| --- |
| language: |
| - tr |
| tags: |
| - sentence-transformers |
| - sentence-similarity |
| - feature-extraction |
| - generated_from_trainer |
| - dataset_size:482091 |
| - loss:MatryoshkaLoss |
| - loss:MultipleNegativesRankingLoss |
| - loss:CoSENTLoss |
| base_model: Alibaba-NLP/gte-multilingual-base |
| widget: |
| - source_sentence: Ya da dışarı çıkıp yürü ya da biraz koşun. Bunu düzenli olarak |
| yapmıyorum ama Washington bunu yapmak için harika bir yer. |
| sentences: |
| - “Washington's yürüyüş ya da koşu için harika bir yer.” |
| - H-2A uzaylılar Amerika Birleşik Devletleri'nde zaman kısa süreleri var. |
| - “Washington'da düzenli olarak yürüyüşe ya da koşuya çıkıyorum.” |
| - source_sentence: Orta yaylalar ve güney kıyıları arasındaki kontrast daha belirgin |
| olamazdı. |
| sentences: |
| - İşitme Yardımı Uyumluluğu Müzakere Kuralları Komitesi, Federal İletişim Komisyonu'nun |
| bir ürünüdür. |
| - Dağlık ve sahil arasındaki kontrast kolayca işaretlendi. |
| - Kontrast işaretlenemedi. |
| - source_sentence: Bir 1997 Henry J. Kaiser Aile Vakfı anket yönetilen bakım planlarında |
| Amerikalılar temelde kendi bakımı ile memnun olduğunu bulundu. |
| sentences: |
| - Kaplanları takip ederken çok sessiz olmalısın. |
| - Henry Kaiser vakfı insanların sağlık hizmetlerinden hoşlandığını gösteriyor. |
| - Henry Kaiser Vakfı insanların sağlık hizmetlerinden nefret ettiğini gösteriyor. |
| - source_sentence: Eminim yapmışlardır. |
| sentences: |
| - Eminim öyle yapmışlardır. |
| - Batı Teksas'ta 100 10 dereceydi. |
| - Eminim yapmamışlardır. |
| - source_sentence: Ve gerçekten, baba haklıydı, oğlu zaten her şeyi tecrübe etmişti, |
| her şeyi denedi ve daha az ilgileniyordu. |
| sentences: |
| - Oğlu her şeye olan ilgisini kaybediyordu. |
| - Pek bir şey yapmadım. |
| - Baba oğlunun tecrübe için hala çok şey olduğunu biliyordu. |
| datasets: |
| - emrecan/all-nli-tr |
| pipeline_tag: sentence-similarity |
| library_name: sentence-transformers |
| metrics: |
| - cosine_accuracy |
| - pearson_cosine |
| - spearman_cosine |
| model-index: |
| - name: SentenceTransformer based on Alibaba-NLP/gte-multilingual-base |
| results: |
| - task: |
| type: triplet |
| name: Triplet |
| dataset: |
| name: all nli tr test |
| type: all-nli-tr-test |
| metrics: |
| - type: cosine_accuracy |
| value: 0.8966145437983908 |
| name: Cosine Accuracy |
| - type: cosine_accuracy |
| value: 0.9351753453772582 |
| name: Cosine Accuracy |
| - task: |
| type: semantic-similarity |
| name: Semantic Similarity |
| dataset: |
| name: sts test |
| type: sts-test |
| metrics: |
| - type: pearson_cosine |
| value: 0.8043925123766598 |
| name: Pearson Cosine |
| - type: spearman_cosine |
| value: 0.804133282756889 |
| name: Spearman Cosine |
| - type: pearson_cosine |
| value: 0.8133873820848544 |
| name: Pearson Cosine |
| - type: spearman_cosine |
| value: 0.8199552151367876 |
| name: Spearman Cosine |
| - task: |
| type: semantic-similarity |
| name: Semantic Similarity |
| dataset: |
| name: sts22 test |
| type: sts22-test |
| metrics: |
| - type: pearson_cosine |
| value: 0.647912337747937 |
| name: Pearson Cosine |
| - type: spearman_cosine |
| value: 0.6694072470896322 |
| name: Spearman Cosine |
| - type: pearson_cosine |
| value: 0.6514085062457564 |
| name: Pearson Cosine |
| - type: spearman_cosine |
| value: 0.6827342891126081 |
| name: Spearman Cosine |
| - task: |
| type: semantic-similarity |
| name: Semantic Similarity |
| dataset: |
| name: sts dev gte multilingual base |
| type: sts-dev-gte-multilingual-base |
| metrics: |
| - type: pearson_cosine |
| value: 0.838717139426684 |
| name: Pearson Cosine |
| - type: spearman_cosine |
| value: 0.8428367492381358 |
| name: Spearman Cosine |
| - task: |
| type: semantic-similarity |
| name: Semantic Similarity |
| dataset: |
| name: sts test gte multilingual base |
| type: sts-test-gte-multilingual-base |
| metrics: |
| - type: pearson_cosine |
| value: 0.8133873820848544 |
| name: Pearson Cosine |
| - type: spearman_cosine |
| value: 0.8199552151367876 |
| name: Spearman Cosine |
| - task: |
| type: semantic-similarity |
| name: Semantic Similarity |
| dataset: |
| name: stsb dev 768 |
| type: stsb-dev-768 |
| metrics: |
| - type: pearson_cosine |
| value: 0.870311456444647 |
| name: Pearson Cosine |
| - type: spearman_cosine |
| value: 0.8747522169942328 |
| name: Spearman Cosine |
| - task: |
| type: semantic-similarity |
| name: Semantic Similarity |
| dataset: |
| name: stsb dev 512 |
| type: stsb-dev-512 |
| metrics: |
| - type: pearson_cosine |
| value: 0.8696934286998554 |
| name: Pearson Cosine |
| - type: spearman_cosine |
| value: 0.8753487201891684 |
| name: Spearman Cosine |
| - task: |
| type: semantic-similarity |
| name: Semantic Similarity |
| dataset: |
| name: stsb dev 256 |
| type: stsb-dev-256 |
| metrics: |
| - type: pearson_cosine |
| value: 0.8644706498119142 |
| name: Pearson Cosine |
| - type: spearman_cosine |
| value: 0.873468734899321 |
| name: Spearman Cosine |
| - task: |
| type: semantic-similarity |
| name: Semantic Similarity |
| dataset: |
| name: stsb dev 128 |
| type: stsb-dev-128 |
| metrics: |
| - type: pearson_cosine |
| value: 0.8591309130178328 |
| name: Pearson Cosine |
| - type: spearman_cosine |
| value: 0.8700377378574327 |
| name: Spearman Cosine |
| - task: |
| type: semantic-similarity |
| name: Semantic Similarity |
| dataset: |
| name: stsb dev 64 |
| type: stsb-dev-64 |
| metrics: |
| - type: pearson_cosine |
| value: 0.8479124810212979 |
| name: Pearson Cosine |
| - type: spearman_cosine |
| value: 0.8655596653561272 |
| name: Spearman Cosine |
| - task: |
| type: semantic-similarity |
| name: Semantic Similarity |
| dataset: |
| name: stsb test 768 |
| type: stsb-test-768 |
| metrics: |
| - type: pearson_cosine |
| value: 0.8455412308380735 |
| name: Pearson Cosine |
| - type: spearman_cosine |
| value: 0.8535290217691063 |
| name: Spearman Cosine |
| - task: |
| type: semantic-similarity |
| name: Semantic Similarity |
| dataset: |
| name: stsb test 512 |
| type: stsb-test-512 |
| metrics: |
| - type: pearson_cosine |
| value: 0.8464773608783734 |
| name: Pearson Cosine |
| - type: spearman_cosine |
| value: 0.8553900248212041 |
| name: Spearman Cosine |
| - task: |
| type: semantic-similarity |
| name: Semantic Similarity |
| dataset: |
| name: stsb test 256 |
| type: stsb-test-256 |
| metrics: |
| - type: pearson_cosine |
| value: 0.8443046458551826 |
| name: Pearson Cosine |
| - type: spearman_cosine |
| value: 0.8550098621393595 |
| name: Spearman Cosine |
| - task: |
| type: semantic-similarity |
| name: Semantic Similarity |
| dataset: |
| name: stsb test 128 |
| type: stsb-test-128 |
| metrics: |
| - type: pearson_cosine |
| value: 0.8363964421208214 |
| name: Pearson Cosine |
| - type: spearman_cosine |
| value: 0.8511193715667303 |
| name: Spearman Cosine |
| - task: |
| type: semantic-similarity |
| name: Semantic Similarity |
| dataset: |
| name: stsb test 64 |
| type: stsb-test-64 |
| metrics: |
| - type: pearson_cosine |
| value: 0.8235450515966374 |
| name: Pearson Cosine |
| - type: spearman_cosine |
| value: 0.8460761238725121 |
| name: Spearman Cosine |
| --- |
| |
| # SentenceTransformer based on Alibaba-NLP/gte-multilingual-base |
|
|
| This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Alibaba-NLP/gte-multilingual-base](https://huggingface.co/Alibaba-NLP/gte-multilingual-base) on the [all-nli-tr](https://huggingface.co/datasets/emrecan/all-nli-tr) 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:** [Alibaba-NLP/gte-multilingual-base](https://huggingface.co/Alibaba-NLP/gte-multilingual-base) <!-- at revision ca1791e0bcc104f6db161f27de1340241b13c5a4 --> |
| - **Maximum Sequence Length:** 512 tokens |
| - **Output Dimensionality:** 768 dimensions |
| - **Similarity Function:** Cosine Similarity |
| - **Training Dataset:** |
| - [all-nli-tr](https://huggingface.co/datasets/emrecan/all-nli-tr) |
| - **Language:** tr |
| <!-- - **License:** Unknown --> |
|
|
| ### 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: NewModel |
| (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 = [ |
| 'Ve gerçekten, baba haklıydı, oğlu zaten her şeyi tecrübe etmişti, her şeyi denedi ve daha az ilgileniyordu.', |
| 'Oğlu her şeye olan ilgisini kaybediyordu.', |
| 'Baba oğlunun tecrübe için hala çok şey olduğunu biliyordu.', |
| ] |
| 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 |
|
|
| #### Triplet |
|
|
| * Dataset: `all-nli-tr-test` |
| * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) |
|
|
| | Metric | Value | |
| |:--------------------|:-----------| |
| | **cosine_accuracy** | **0.8966** | |
| |
| #### Semantic Similarity |
| |
| * Datasets: `sts-test`, `sts22-test`, `sts-dev-gte-multilingual-base`, `sts-test-gte-multilingual-base`, `sts-test`, `sts22-test`, `stsb-dev-768`, `stsb-dev-512`, `stsb-dev-256`, `stsb-dev-128`, `stsb-dev-64`, `stsb-test-768`, `stsb-test-512`, `stsb-test-256`, `stsb-test-128` and `stsb-test-64` |
| * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) |
| |
| | Metric | sts-test | sts22-test | sts-dev-gte-multilingual-base | sts-test-gte-multilingual-base | stsb-dev-768 | stsb-dev-512 | stsb-dev-256 | stsb-dev-128 | stsb-dev-64 | stsb-test-768 | stsb-test-512 | stsb-test-256 | stsb-test-128 | stsb-test-64 | |
| |:--------------------|:---------|:-----------|:------------------------------|:-------------------------------|:-------------|:-------------|:-------------|:-------------|:------------|:--------------|:--------------|:--------------|:--------------|:-------------| |
| | pearson_cosine | 0.8134 | 0.6514 | 0.8387 | 0.8134 | 0.8703 | 0.8697 | 0.8645 | 0.8591 | 0.8479 | 0.8455 | 0.8465 | 0.8443 | 0.8364 | 0.8235 | |
| | **spearman_cosine** | **0.82** | **0.6827** | **0.8428** | **0.82** | **0.8748** | **0.8753** | **0.8735** | **0.87** | **0.8656** | **0.8535** | **0.8554** | **0.855** | **0.8511** | **0.8461** | |
| |
| #### Triplet |
| |
| * Dataset: `all-nli-tr-test` |
| * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) |
| |
| | Metric | Value | |
| |:--------------------|:-----------| |
| | **cosine_accuracy** | **0.9352** | |
| |
| <!-- |
| ## 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 |
| |
| #### all-nli-tr |
| |
| * Dataset: [all-nli-tr](https://huggingface.co/datasets/emrecan/all-nli-tr) at [daeabfb](https://huggingface.co/datasets/emrecan/all-nli-tr/tree/daeabfbc01f82757ab998bd23ce0ddfceaa5e24d) |
| * Size: 482,091 training samples |
| * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code> |
| * Approximate statistics based on the first 1000 samples: |
| | | sentence1 | sentence2 | score | |
| |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------| |
| | type | string | string | float | |
| | details | <ul><li>min: 6 tokens</li><li>mean: 10.51 tokens</li><li>max: 27 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 10.47 tokens</li><li>max: 27 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 2.23</li><li>max: 5.0</li></ul> | |
| * Samples: |
| | sentence1 | sentence2 | score | |
| |:----------------------------------------------------------|:-------------------------------------------------------------------|:-----------------| |
| | <code>Bir uçak kalkıyor.</code> | <code>Bir hava uçağı kalkıyor.</code> | <code>5.0</code> | |
| | <code>Bir adam büyük bir flüt çalıyor.</code> | <code>Bir adam flüt çalıyor.</code> | <code>3.8</code> | |
| | <code>Bir adam pizzaya rendelenmiş peynir yayıyor.</code> | <code>Bir adam pişmemiş pizzaya rendelenmiş peynir yayıyor.</code> | <code>3.8</code> | |
| * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters: |
| ```json |
| { |
| "loss": "CoSENTLoss", |
| "matryoshka_dims": [ |
| 768, |
| 512, |
| 256, |
| 128, |
| 64 |
| ], |
| "matryoshka_weights": [ |
| 1, |
| 1, |
| 1, |
| 1, |
| 1 |
| ], |
| "n_dims_per_step": -1 |
| } |
| ``` |
| |
| ### Evaluation Dataset |
|
|
| #### all-nli-tr |
|
|
| * Dataset: [all-nli-tr](https://huggingface.co/datasets/emrecan/all-nli-tr) at [daeabfb](https://huggingface.co/datasets/emrecan/all-nli-tr/tree/daeabfbc01f82757ab998bd23ce0ddfceaa5e24d) |
| * Size: 6,567 evaluation samples |
| * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code> |
| * Approximate statistics based on the first 1000 samples: |
| | | sentence1 | sentence2 | score | |
| |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------| |
| | type | string | string | float | |
| | details | <ul><li>min: 6 tokens</li><li>mean: 15.89 tokens</li><li>max: 39 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.02 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 2.1</li><li>max: 5.0</li></ul> | |
| * Samples: |
| | sentence1 | sentence2 | score | |
| |:---------------------------------------------|:----------------------------------------------------|:------------------| |
| | <code>Şapkalı bir adam dans ediyor.</code> | <code>Sert şapka takan bir adam dans ediyor.</code> | <code>5.0</code> | |
| | <code>Küçük bir çocuk ata biniyor.</code> | <code>Bir çocuk ata biniyor.</code> | <code>4.75</code> | |
| | <code>Bir adam yılana fare yediriyor.</code> | <code>Adam yılana fare yediriyor.</code> | <code>5.0</code> | |
| * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters: |
| ```json |
| { |
| "loss": "CoSENTLoss", |
| "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`: steps |
| - `per_device_train_batch_size`: 32 |
| - `per_device_eval_batch_size`: 32 |
| - `learning_rate`: 1e-05 |
| - `weight_decay`: 0.01 |
| - `num_train_epochs`: 10 |
| - `warmup_ratio`: 0.1 |
| - `warmup_steps`: 144 |
| - `bf16`: True |
|
|
| #### All Hyperparameters |
| <details><summary>Click to expand</summary> |
|
|
| - `overwrite_output_dir`: False |
| - `do_predict`: False |
| - `eval_strategy`: steps |
| - `prediction_loss_only`: True |
| - `per_device_train_batch_size`: 32 |
| - `per_device_eval_batch_size`: 32 |
| - `per_gpu_train_batch_size`: None |
| - `per_gpu_eval_batch_size`: None |
| - `gradient_accumulation_steps`: 1 |
| - `eval_accumulation_steps`: None |
| - `torch_empty_cache_steps`: None |
| - `learning_rate`: 1e-05 |
| - `weight_decay`: 0.01 |
| - `adam_beta1`: 0.9 |
| - `adam_beta2`: 0.999 |
| - `adam_epsilon`: 1e-08 |
| - `max_grad_norm`: 1.0 |
| - `num_train_epochs`: 10 |
| - `max_steps`: -1 |
| - `lr_scheduler_type`: linear |
| - `lr_scheduler_kwargs`: {} |
| - `warmup_ratio`: 0.1 |
| - `warmup_steps`: 144 |
| - `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`: False |
| - `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 |
| - `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`: batch_sampler |
| - `multi_dataset_batch_sampler`: proportional |
|
|
| </details> |
|
|
| ### Training Logs |
| | Epoch | Step | Training Loss | Validation Loss | all-nli-tr-test_cosine_accuracy | sts-test_spearman_cosine | sts22-test_spearman_cosine | sts-dev-gte-multilingual-base_spearman_cosine | sts-test-gte-multilingual-base_spearman_cosine | stsb-dev-768_spearman_cosine | stsb-dev-512_spearman_cosine | stsb-dev-256_spearman_cosine | stsb-dev-128_spearman_cosine | stsb-dev-64_spearman_cosine | stsb-test-768_spearman_cosine | stsb-test-512_spearman_cosine | stsb-test-256_spearman_cosine | stsb-test-128_spearman_cosine | stsb-test-64_spearman_cosine | |
| |:------:|:----:|:-------------:|:---------------:|:-------------------------------:|:------------------------:|:--------------------------:|:---------------------------------------------:|:----------------------------------------------:|:----------------------------:|:----------------------------:|:----------------------------:|:----------------------------:|:---------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:----------------------------:| |
| | 0 | 0 | - | - | 0.8966 | 0.8041 | 0.6694 | - | - | - | - | - | - | - | - | - | - | - | - | |
| | 0.1327 | 1000 | 2.5299 | 3.3893 | - | - | - | 0.8318 | - | - | - | - | - | - | - | - | - | - | - | |
| | 0.2655 | 2000 | 2.1132 | 3.3050 | - | - | - | 0.8345 | - | - | - | - | - | - | - | - | - | - | - | |
| | 0.3982 | 3000 | 5.1488 | 2.7752 | - | - | - | 0.8481 | - | - | - | - | - | - | - | - | - | - | - | |
| | 0.5310 | 4000 | 5.4103 | 2.7242 | - | - | - | 0.8445 | - | - | - | - | - | - | - | - | - | - | - | |
| | 0.6637 | 5000 | 5.1896 | 2.6701 | - | - | - | 0.8451 | - | - | - | - | - | - | - | - | - | - | - | |
| | 0.7965 | 6000 | 5.0105 | 2.6489 | - | - | - | 0.8431 | - | - | - | - | - | - | - | - | - | - | - | |
| | 0.9292 | 7000 | 5.1059 | 2.6114 | - | - | - | 0.8428 | - | - | - | - | - | - | - | - | - | - | - | |
| | 1.0 | 7533 | - | - | 0.9352 | 0.8200 | 0.6827 | - | 0.8200 | - | - | - | - | - | - | - | - | - | - | |
| | 1.1111 | 200 | 34.2828 | 29.8737 | - | - | - | - | - | 0.8671 | 0.8671 | 0.8639 | 0.8606 | 0.8546 | - | - | - | - | - | |
| | 2.2222 | 400 | 28.038 | 28.8915 | - | - | - | - | - | 0.8740 | 0.8742 | 0.8720 | 0.8691 | 0.8648 | - | - | - | - | - | |
| | 3.3333 | 600 | 27.3829 | 29.3391 | - | - | - | - | - | 0.8747 | 0.8751 | 0.8728 | 0.8699 | 0.8653 | - | - | - | - | - | |
| | 4.4444 | 800 | 26.807 | 30.0090 | - | - | - | - | - | 0.8756 | 0.8761 | 0.8741 | 0.8710 | 0.8665 | - | - | - | - | - | |
| | 5.5556 | 1000 | 26.4543 | 30.5886 | - | - | - | - | - | 0.8753 | 0.8757 | 0.8739 | 0.8705 | 0.8662 | - | - | - | - | - | |
| | 6.6667 | 1200 | 26.0413 | 31.3750 | - | - | - | - | - | 0.8744 | 0.8751 | 0.8730 | 0.8698 | 0.8655 | - | - | - | - | - | |
| | 7.7778 | 1400 | 25.8221 | 31.6515 | - | - | - | - | - | 0.8752 | 0.8758 | 0.8739 | 0.8706 | 0.8661 | - | - | - | - | - | |
| | 8.8889 | 1600 | 25.6656 | 31.9805 | - | - | - | - | - | 0.8746 | 0.8752 | 0.8733 | 0.8700 | 0.8655 | - | - | - | - | - | |
| | 10.0 | 1800 | 25.5355 | 32.0454 | - | - | - | - | - | 0.8748 | 0.8753 | 0.8735 | 0.8700 | 0.8656 | 0.8535 | 0.8554 | 0.8550 | 0.8511 | 0.8461 | |
|
|
|
|
| ### Framework Versions |
| - Python: 3.11.11 |
| - Sentence Transformers: 3.3.1 |
| - Transformers: 4.49.0.dev0 |
| - PyTorch: 2.5.1+cu121 |
| - Accelerate: 1.2.1 |
| - 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} |
| } |
| ``` |
|
|
| #### CoSENTLoss |
| ```bibtex |
| @online{kexuefm-8847, |
| title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT}, |
| author={Su Jianlin}, |
| year={2022}, |
| month={Jan}, |
| url={https://kexue.fm/archives/8847}, |
| } |
| ``` |
|
|
| <!-- |
| ## 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.* |
| --> |
