Add new SentenceTransformer model.

.gitattributes

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

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,640 @@
+---
+base_model: intfloat/multilingual-e5-small
+language:
+- multilingual
+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:94
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: 서울여자대학교 수시모집 지원자에게 필요한 최초합격자 발표 정보는 다음과 같습니다. 최초합격자 발표는 2024년 11월
+    8일부터 12월 13일까지입니다. 합격자는 본교 입학처 홈페이지에서 합격 여부를 확인하여야 하며, 등록기간 내에 등록을 마쳐야 합니다.
+  sentences:
+  - SWU의 SI(Social Innovation)교육에 대해 알려줘.
+  - 학교생활기록부 교과성적 반영방법을 설명해 주세요.
+  - 서울여자대학교 수시모집 지원자에게 필요한 최초합격자 발표 정보를 알려줘.
+- source_sentence: 고등학교 졸업(예정)자의 경우 학교생활기록부 제출 방법은 다음과 같습니다. 원본 대조필 및 학교장 직인 날인 후
+    제출하여야 합니다. 외국 고등학교 졸업(예정)자의 경우는 한국어나 영어로 번역 공증받은 문서를 제출하여야 합니다.
+  sentences:
+  - 언론영상학부-저널리즘전공의 졸업 후 진로는 무엇입니까?
+  - 서울여자대학교에 있는 박물관학전공의 교육 내용을 설명해줘.
+  - 고등학교 졸업(예정)자의 경우 학교생활기록부 제출 방법을 설명해줘.
+- source_sentence: 심리·인지과학학부-인지학습과학전공의 졸업 후 진로는 교육프로그램 개발자, 교육기업 데이터 분석 업무, 인지학습 치료사,
+    인지행동 치료사, 교육컨설턴트, 국가연구소, 이러닝 관련 산업분야 등입니다.
+  sentences:
+  - 서울여자대학교에 있는 예술심리치료전공의 목표를 설명해줘.
+  - 서울여자대학교 수시모집 지원자에게 필요한 교과성적 산출 방법을 설명해줘.
+  - 심리·인지과학학부-인지학습과학전공의 졸업 후 진로를 설명하세요.
+- source_sentence: 2024학년도 서울여자대학교 수시모집 지원자에게 필요한 정보는 다음과 같습니다. 수시모집 지원기간은 2024년 9월
+    10일부터 9월 13일까지입니다. 지원자는 인터넷 입학원서접수 사이트에 접속하여 원서접수를 완료해야 하며, 전형료 결제는 신용카드, 계좌이체
+    등으로 가능합니다. 또한, 지원자는 제출서류를 등기우편으로 제출하여야 하며, 서류제출 마감일은 2024년 9월 13일입니다.
+  sentences:
+  - 박물관학전공의 교육 목표는 무엇입니까?
+  - 2024학년도 서울여자대학교 수시모집 지원자에게 필요한 정보를 알려줘.
+  - 학생부종합 전형으로 지원할 수 있는 전형의 유형을 모두 알려줘
+- source_sentence: 학교생활기록부 교과성적 대체 점수(비교내신) 대상자는 논술(논술우수자전형), 실기/실적(실기우수자전형_체육) 지원자
+    중 고등학교 졸업학력 검정고시 출신 지원자 및 교과성적 산출 불가자입니다.
+  sentences:
+  - 고등학교 학교생활기록부 제출 방법을 설명하세요.
+  - 청소년학전공의 교육 내용은 무엇입니까?
+  - 학교생활기록부 교과성적 대체 점수(비교내신) 대상자를 알려줘.
+model-index:
+- name: Multilingual base SWU Matryoshka
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6363636363636364
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9090909090909091
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 1.0
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 1.0
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6363636363636364
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.30303030303030304
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.2
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.1
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6363636363636364
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9090909090909091
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 1.0
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 1.0
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8475878017079786
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7954545454545454
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7954545454545454
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6363636363636364
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9090909090909091
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 1.0
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 1.0
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6363636363636364
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.30303030303030304
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.2
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.1
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6363636363636364
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9090909090909091
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 1.0
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 1.0
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8475878017079786
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7954545454545454
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7954545454545454
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6363636363636364
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9090909090909091
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 1.0
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 1.0
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6363636363636364
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.30303030303030304
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.2
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.1
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6363636363636364
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9090909090909091
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 1.0
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 1.0
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8356850968378461
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7803030303030302
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7803030303030302
+      name: Cosine Map@100
+---
+
+# Multilingual base SWU Matryoshka
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) on the json dataset. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) <!-- at revision fd1525a9fd15316a2d503bf26ab031a61d056e98 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 384 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - json
+- **Language:** multilingual
+- **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': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## 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("ValentinaKim/Multilingual-base-SWU-Matryoshka")
+# Run inference
+sentences = [
+    '학교생활기록부 교과성적 대체 점수(비교내신) 대상자는 논술(논술우수자전형), 실기/실적(실기우수자전형_체육) 지원자 중 고등학교 졸업학력 검정고시 출신 지원자 및 교과성적 산출 불가자입니다.',
+    '학교생활기록부 교과성적 대체 점수(비교내신) 대상자를 알려줘.',
+    '청소년학전공의 교육 내용은 무엇입니까?',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# 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_256`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.6364     |
+| cosine_accuracy@3   | 0.9091     |
+| cosine_accuracy@5   | 1.0        |
+| cosine_accuracy@10  | 1.0        |
+| cosine_precision@1  | 0.6364     |
+| cosine_precision@3  | 0.303      |
+| cosine_precision@5  | 0.2        |
+| cosine_precision@10 | 0.1        |
+| cosine_recall@1     | 0.6364     |
+| cosine_recall@3     | 0.9091     |
+| cosine_recall@5     | 1.0        |
+| cosine_recall@10    | 1.0        |
+| cosine_ndcg@10      | 0.8476     |
+| cosine_mrr@10       | 0.7955     |
+| **cosine_map@100**  | **0.7955** |
+
+#### 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   | 0.6364     |
+| cosine_accuracy@3   | 0.9091     |
+| cosine_accuracy@5   | 1.0        |
+| cosine_accuracy@10  | 1.0        |
+| cosine_precision@1  | 0.6364     |
+| cosine_precision@3  | 0.303      |
+| cosine_precision@5  | 0.2        |
+| cosine_precision@10 | 0.1        |
+| cosine_recall@1     | 0.6364     |
+| cosine_recall@3     | 0.9091     |
+| cosine_recall@5     | 1.0        |
+| cosine_recall@10    | 1.0        |
+| cosine_ndcg@10      | 0.8476     |
+| cosine_mrr@10       | 0.7955     |
+| **cosine_map@100**  | **0.7955** |
+
+#### Information Retrieval
+* Dataset: `dim_64`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.6364     |
+| cosine_accuracy@3   | 0.9091     |
+| cosine_accuracy@5   | 1.0        |
+| cosine_accuracy@10  | 1.0        |
+| cosine_precision@1  | 0.6364     |
+| cosine_precision@3  | 0.303      |
+| cosine_precision@5  | 0.2        |
+| cosine_precision@10 | 0.1        |
+| cosine_recall@1     | 0.6364     |
+| cosine_recall@3     | 0.9091     |
+| cosine_recall@5     | 1.0        |
+| cosine_recall@10    | 1.0        |
+| cosine_ndcg@10      | 0.8357     |
+| cosine_mrr@10       | 0.7803     |
+| **cosine_map@100**  | **0.7803** |
+
+<!--
+## 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: 94 training samples
+* Columns: <code>positive</code> and <code>anchor</code>
+* Approximate statistics based on the first 94 samples:
+  |         | positive                                                                            | anchor                                                                             |
+  |:--------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                             |
+  | details | <ul><li>min: 24 tokens</li><li>mean: 89.93 tokens</li><li>max: 272 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 19.18 tokens</li><li>max: 35 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                               | anchor                                               |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------|
+  | <code>서울여자대학교 수시모집에서 평가하는 요소는 다음과 같습니다. 1. 서류 평가(학업역량 40%, 진로역량 35%, 공동체역량 25%) 2. 면접 평가(인성 및 의사소통능력, 발전가능성) 3. 학교생활기록부에 학교폭력 관련 기재사항이 있을 경우, 정성평가로 반영합니다.</code>                      | <code>서울여자대학교 수시모집에서 평가하는 요소를 알려줘.</code>            |
+  | <code>서울여자대학교 학생부종합전형 지원자에게 필요한 지원자격 정보는 다음과 같습니다. 지원자격은 기초생활수급자, 차상위계층, 한부모가족 지원대상자, 국가보훈대상자, 자립지원 대상 아동, 농어촌학생 등입니다. 각 지원자격에 따라 필요한 제출서류가 다르므로, 지원자격에 따라 필요한 제출서류를 확인하여야 합니다.</code> | <code>서울여자대학교 학생부종합전형 지원자에게 필요한 지원자격 정보를 알려줘.</code> |
+  | <code>SWU의 SI(Social Innovation)교육은 사회적 가치 확산을 위해 혁신적인 방법론을 적용하여 긍정적인 사회 변화를 유도하는 서울여자대학교만의 차별화된 교육입니다. 바롬종합설계프로젝트는 유네스코한국위원회가 인증한 유네스코지속가능발전교육공식프로젝트입니다.</code>                       | <code>SWU의 SI(Social Innovation)교육에 대해 알려줘.</code>   |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 4
+- `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`: 8
+- `per_device_eval_batch_size`: 8
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: 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`: 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
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch   | Step  | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_64_cosine_map@100 |
+|:-------:|:-----:|:----------------------:|:----------------------:|:---------------------:|
+| **1.0** | **1** | **0.7955**             | **0.7955**             | **0.7803**            |
+| 2.0     | 2     | 0.7955                 | 0.7955                 | 0.7803                |
+| 3.0     | 4     | 0.7955                 | 0.7955                 | 0.7803                |
+| **1.0** | **1** | **0.7955**             | **0.7955**             | **0.7803**            |
+| 2.0     | 2     | 0.7955                 | 0.7955                 | 0.7803                |
+| 3.0     | 4     | 0.7955                 | 0.7955                 | 0.7803                |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.14
+- Sentence Transformers: 3.1.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+cu121
+- Accelerate: 0.34.2
+- Datasets: 2.19.1
+- Tokenizers: 0.19.1
+
+## 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 +1,26 @@
+{
+  "_name_or_path": "intfloat/multilingual-e5-small",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "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",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.1.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.2+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:249a1637291f537f82450c7618fd21a5e44441273ca005127e7163879e59fbc7
+size 470637416

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": false
+}

sentencepiece.bpe.model

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

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef04f2b385d1514f500e779207ace0f53e30895ce37563179e29f4022d28ca38
+size 17083053

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}