--- base_model: aubmindlab/bert-base-arabertv02 datasets: [] language: [] library_name: sentence-transformers metrics: - pearson_cosine - spearman_cosine - pearson_manhattan - spearman_manhattan - pearson_euclidean - spearman_euclidean - pearson_dot - spearman_dot - pearson_max - spearman_max pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:1000000 - loss:MatryoshkaLoss - loss:MultipleNegativesRankingLoss widget: - source_sentence: فتى يرتدي اللون الأحمر ينزلق على متن عربة نفخة sentences: - اثنان من الشباب الآسيويين يتسكعون - فتى يلعب على عربة نفخة - فتى يثقب سكيناً في عربة نفخة - source_sentence: عامل بناء يقف على رافعة يضع ذراعًا كبيرًا على قمة قمة قيد الإنشاء. sentences: - الاطفال يركبون عربة متعة - شخص يقف - لا أحد يقف - source_sentence: رجل مع حفرة طاقة كبيرة يقف بجانب ابنته مع خرطوم المكنسة الكهربائية. sentences: - جنديان يحملان أسلحة - رجل يحمل مثقاب يقف بجانب فتاة تحمل خرطوم كهربائي - الرجل والفتاة يرسمون الجدران - source_sentence: رجل يرتدي قميص أسود يعزف على الجيتار. sentences: - الرجل يرتدي الأسود. - هناك رجل يفرغ - الرجل يرتدي قميصاً أزرق. - source_sentence: رجل يرتدي قميص (فيجاس) الأحمر يجلس على طاولة ويلعب بالكاميرا sentences: - رجل يلعب بالكاميرا - فتى يقفز في الهواء - الرجل يقف ويأخذ الصور model-index: - name: SentenceTransformer based on aubmindlab/bert-base-arabertv02 results: - task: type: semantic-similarity name: Semantic Similarity dataset: name: sts test 768 type: sts-test-768 metrics: - type: pearson_cosine value: 0.8137491067613172 name: Pearson Cosine - type: spearman_cosine value: 0.8139804248887779 name: Spearman Cosine - type: pearson_manhattan value: 0.805239691712325 name: Pearson Manhattan - type: spearman_manhattan value: 0.8071457719582591 name: Spearman Manhattan - type: pearson_euclidean value: 0.8053105962459932 name: Pearson Euclidean - type: spearman_euclidean value: 0.8078084689219578 name: Spearman Euclidean - type: pearson_dot value: 0.8019135317246738 name: Pearson Dot - type: spearman_dot value: 0.7961388104098682 name: Spearman Dot - type: pearson_max value: 0.8137491067613172 name: Pearson Max - type: spearman_max value: 0.8139804248887779 name: Spearman Max - type: pearson_cosine value: 0.8137491067613172 name: Pearson Cosine - type: spearman_cosine value: 0.8139804248887779 name: Spearman Cosine - type: pearson_manhattan value: 0.805239691712325 name: Pearson Manhattan - type: spearman_manhattan value: 0.8071457719582591 name: Spearman Manhattan - type: pearson_euclidean value: 0.8053105962459932 name: Pearson Euclidean - type: spearman_euclidean value: 0.8078084689219578 name: Spearman Euclidean - type: pearson_dot value: 0.8019135317246738 name: Pearson Dot - type: spearman_dot value: 0.7961388104098682 name: Spearman Dot - type: pearson_max value: 0.8137491067613172 name: Pearson Max - type: spearman_max value: 0.8139804248887779 name: Spearman Max - task: type: semantic-similarity name: Semantic Similarity dataset: name: sts test 512 type: sts-test-512 metrics: - type: pearson_cosine value: 0.8127890716639393 name: Pearson Cosine - type: spearman_cosine value: 0.813769735512917 name: Spearman Cosine - type: pearson_manhattan value: 0.8045619532064516 name: Pearson Manhattan - type: spearman_manhattan value: 0.806084784718251 name: Spearman Manhattan - type: pearson_euclidean value: 0.8047817340341926 name: Pearson Euclidean - type: spearman_euclidean value: 0.8067787363048019 name: Spearman Euclidean - type: pearson_dot value: 0.7985706834990611 name: Pearson Dot - type: spearman_dot value: 0.7926669266198092 name: Spearman Dot - type: pearson_max value: 0.8127890716639393 name: Pearson Max - type: spearman_max value: 0.813769735512917 name: Spearman Max - type: pearson_cosine value: 0.8127890716639393 name: Pearson Cosine - type: spearman_cosine value: 0.813769735512917 name: Spearman Cosine - type: pearson_manhattan value: 0.8045619532064516 name: Pearson Manhattan - type: spearman_manhattan value: 0.806084784718251 name: Spearman Manhattan - type: pearson_euclidean value: 0.8047817340341926 name: Pearson Euclidean - type: spearman_euclidean value: 0.8067787363048019 name: Spearman Euclidean - type: pearson_dot value: 0.7985706834990611 name: Pearson Dot - type: spearman_dot value: 0.7926669266198092 name: Spearman Dot - type: pearson_max value: 0.8127890716639393 name: Pearson Max - type: spearman_max value: 0.813769735512917 name: Spearman Max - task: type: semantic-similarity name: Semantic Similarity dataset: name: sts test 256 type: sts-test-256 metrics: - type: pearson_cosine value: 0.810388221021721 name: Pearson Cosine - type: spearman_cosine value: 0.8138356923403065 name: Spearman Cosine - type: pearson_manhattan value: 0.8015100804443567 name: Pearson Manhattan - type: spearman_manhattan value: 0.8026219149891689 name: Spearman Manhattan - type: pearson_euclidean value: 0.8016089017435591 name: Pearson Euclidean - type: spearman_euclidean value: 0.8030480833628191 name: Spearman Euclidean - type: pearson_dot value: 0.792265476718613 name: Pearson Dot - type: spearman_dot value: 0.787067391010805 name: Spearman Dot - type: pearson_max value: 0.810388221021721 name: Pearson Max - type: spearman_max value: 0.8138356923403065 name: Spearman Max - type: pearson_cosine value: 0.810388221021721 name: Pearson Cosine - type: spearman_cosine value: 0.8138356923403065 name: Spearman Cosine - type: pearson_manhattan value: 0.8015100804443567 name: Pearson Manhattan - type: spearman_manhattan value: 0.8026219149891689 name: Spearman Manhattan - type: pearson_euclidean value: 0.8016089017435591 name: Pearson Euclidean - type: spearman_euclidean value: 0.8030480833628191 name: Spearman Euclidean - type: pearson_dot value: 0.792265476718613 name: Pearson Dot - type: spearman_dot value: 0.787067391010805 name: Spearman Dot - type: pearson_max value: 0.810388221021721 name: Pearson Max - type: spearman_max value: 0.8138356923403065 name: Spearman Max - task: type: semantic-similarity name: Semantic Similarity dataset: name: sts test 128 type: sts-test-128 metrics: - type: pearson_cosine value: 0.8071777671061434 name: Pearson Cosine - type: spearman_cosine value: 0.8128987608664245 name: Spearman Cosine - type: pearson_manhattan value: 0.7969339482985063 name: Pearson Manhattan - type: spearman_manhattan value: 0.7972524285093451 name: Spearman Manhattan - type: pearson_euclidean value: 0.7971979787664204 name: Pearson Euclidean - type: spearman_euclidean value: 0.797866628579141 name: Spearman Euclidean - type: pearson_dot value: 0.7752745908442699 name: Pearson Dot - type: spearman_dot value: 0.7685950685903284 name: Spearman Dot - type: pearson_max value: 0.8071777671061434 name: Pearson Max - type: spearman_max value: 0.8128987608664245 name: Spearman Max - type: pearson_cosine value: 0.8071777671061434 name: Pearson Cosine - type: spearman_cosine value: 0.8128987608664245 name: Spearman Cosine - type: pearson_manhattan value: 0.7969339482985063 name: Pearson Manhattan - type: spearman_manhattan value: 0.7972524285093451 name: Spearman Manhattan - type: pearson_euclidean value: 0.7971979787664204 name: Pearson Euclidean - type: spearman_euclidean value: 0.797866628579141 name: Spearman Euclidean - type: pearson_dot value: 0.7752745908442699 name: Pearson Dot - type: spearman_dot value: 0.7685950685903284 name: Spearman Dot - type: pearson_max value: 0.8071777671061434 name: Pearson Max - type: spearman_max value: 0.8128987608664245 name: Spearman Max - task: type: semantic-similarity name: Semantic Similarity dataset: name: sts test 64 type: sts-test-64 metrics: - type: pearson_cosine value: 0.7992861493805723 name: Pearson Cosine - type: spearman_cosine value: 0.809205854296297 name: Spearman Cosine - type: pearson_manhattan value: 0.7841737408240652 name: Pearson Manhattan - type: spearman_manhattan value: 0.7848704254075567 name: Spearman Manhattan - type: pearson_euclidean value: 0.7865782078684138 name: Pearson Euclidean - type: spearman_euclidean value: 0.7874610680426495 name: Spearman Euclidean - type: pearson_dot value: 0.7341564461014968 name: Pearson Dot - type: spearman_dot value: 0.7244607540987561 name: Spearman Dot - type: pearson_max value: 0.7992861493805723 name: Pearson Max - type: spearman_max value: 0.809205854296297 name: Spearman Max - type: pearson_cosine value: 0.7992861493805723 name: Pearson Cosine - type: spearman_cosine value: 0.809205854296297 name: Spearman Cosine - type: pearson_manhattan value: 0.7841737408240652 name: Pearson Manhattan - type: spearman_manhattan value: 0.7848704254075567 name: Spearman Manhattan - type: pearson_euclidean value: 0.7865782078684138 name: Pearson Euclidean - type: spearman_euclidean value: 0.7874610680426495 name: Spearman Euclidean - type: pearson_dot value: 0.7341564461014968 name: Pearson Dot - type: spearman_dot value: 0.7244607540987561 name: Spearman Dot - type: pearson_max value: 0.7992861493805723 name: Pearson Max - type: spearman_max value: 0.809205854296297 name: Spearman Max --- # SentenceTransformer based on aubmindlab/bert-base-arabertv02 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02). 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:** [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 tokens - **Similarity Function:** Cosine Similarity ### 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': 768, '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}) ) ``` ## 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("Omartificial-Intelligence-Space/Arabert-matro-v4") # Run inference sentences = [ 'رجل يرتدي قميص (فيجاس) الأحمر يجلس على طاولة ويلعب بالكاميرا', 'رجل يلعب بالكاميرا', 'الرجل يقف ويأخذ الصور', ] 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] ``` ## Evaluation ### Metrics #### Semantic Similarity * Dataset: `sts-test-768` * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:----------| | pearson_cosine | 0.8137 | | **spearman_cosine** | **0.814** | | pearson_manhattan | 0.8052 | | spearman_manhattan | 0.8071 | | pearson_euclidean | 0.8053 | | spearman_euclidean | 0.8078 | | pearson_dot | 0.8019 | | spearman_dot | 0.7961 | | pearson_max | 0.8137 | | spearman_max | 0.814 | #### Semantic Similarity * Dataset: `sts-test-512` * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.8128 | | **spearman_cosine** | **0.8138** | | pearson_manhattan | 0.8046 | | spearman_manhattan | 0.8061 | | pearson_euclidean | 0.8048 | | spearman_euclidean | 0.8068 | | pearson_dot | 0.7986 | | spearman_dot | 0.7927 | | pearson_max | 0.8128 | | spearman_max | 0.8138 | #### Semantic Similarity * Dataset: `sts-test-256` * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.8104 | | **spearman_cosine** | **0.8138** | | pearson_manhattan | 0.8015 | | spearman_manhattan | 0.8026 | | pearson_euclidean | 0.8016 | | spearman_euclidean | 0.803 | | pearson_dot | 0.7923 | | spearman_dot | 0.7871 | | pearson_max | 0.8104 | | spearman_max | 0.8138 | #### Semantic Similarity * Dataset: `sts-test-128` * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.8072 | | **spearman_cosine** | **0.8129** | | pearson_manhattan | 0.7969 | | spearman_manhattan | 0.7973 | | pearson_euclidean | 0.7972 | | spearman_euclidean | 0.7979 | | pearson_dot | 0.7753 | | spearman_dot | 0.7686 | | pearson_max | 0.8072 | | spearman_max | 0.8129 | #### Semantic Similarity * Dataset: `sts-test-64` * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.7993 | | **spearman_cosine** | **0.8092** | | pearson_manhattan | 0.7842 | | spearman_manhattan | 0.7849 | | pearson_euclidean | 0.7866 | | spearman_euclidean | 0.7875 | | pearson_dot | 0.7342 | | spearman_dot | 0.7245 | | pearson_max | 0.7993 | | spearman_max | 0.8092 | #### Semantic Similarity * Dataset: `sts-test-768` * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:----------| | pearson_cosine | 0.8137 | | **spearman_cosine** | **0.814** | | pearson_manhattan | 0.8052 | | spearman_manhattan | 0.8071 | | pearson_euclidean | 0.8053 | | spearman_euclidean | 0.8078 | | pearson_dot | 0.8019 | | spearman_dot | 0.7961 | | pearson_max | 0.8137 | | spearman_max | 0.814 | #### Semantic Similarity * Dataset: `sts-test-512` * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.8128 | | **spearman_cosine** | **0.8138** | | pearson_manhattan | 0.8046 | | spearman_manhattan | 0.8061 | | pearson_euclidean | 0.8048 | | spearman_euclidean | 0.8068 | | pearson_dot | 0.7986 | | spearman_dot | 0.7927 | | pearson_max | 0.8128 | | spearman_max | 0.8138 | #### Semantic Similarity * Dataset: `sts-test-256` * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.8104 | | **spearman_cosine** | **0.8138** | | pearson_manhattan | 0.8015 | | spearman_manhattan | 0.8026 | | pearson_euclidean | 0.8016 | | spearman_euclidean | 0.803 | | pearson_dot | 0.7923 | | spearman_dot | 0.7871 | | pearson_max | 0.8104 | | spearman_max | 0.8138 | #### Semantic Similarity * Dataset: `sts-test-128` * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.8072 | | **spearman_cosine** | **0.8129** | | pearson_manhattan | 0.7969 | | spearman_manhattan | 0.7973 | | pearson_euclidean | 0.7972 | | spearman_euclidean | 0.7979 | | pearson_dot | 0.7753 | | spearman_dot | 0.7686 | | pearson_max | 0.8072 | | spearman_max | 0.8129 | #### Semantic Similarity * Dataset: `sts-test-64` * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.7993 | | **spearman_cosine** | **0.8092** | | pearson_manhattan | 0.7842 | | spearman_manhattan | 0.7849 | | pearson_euclidean | 0.7866 | | spearman_euclidean | 0.7875 | | pearson_dot | 0.7342 | | spearman_dot | 0.7245 | | pearson_max | 0.7993 | | spearman_max | 0.8092 | ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 1,000,000 training samples * Columns: anchor, positive, and negative * Approximate statistics based on the first 1000 samples: | | anchor | positive | negative | |:--------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | string | string | string | | details | | | | * Samples: | anchor | positive | negative | |:-----------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------| | ما الذي تتجنبه؟ | ما الذي تحاولين تجنبه دائماً؟ | أنا في حالة اكتئاب ماذا يجب أن أفعل؟ | | رجل يقف عند لافتة صفراء | رجل يقترب من علامة | رجل بجانب لافتة زرقاء | | لماذا قام (مودي) بحظر أوراق نقدية بقيمة 500 و 1000 روبية؟ | لماذا قام مودي بإلغاء عملة الـ 500 و 1000 روبية؟ وما سبب إدخال عملة الـ 2000 روبية فجأة؟ | ما هو أفضل خيار بعد الانتهاء من البكالوريوس في الهندسة الميكانيكية؟ | * Loss: [MatryoshkaLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters: ```json { "loss": "MultipleNegativesRankingLoss", "matryoshka_dims": [ 768, 512, 256, 128, 64 ], "matryoshka_weights": [ 1, 1, 1, 1, 1 ], "n_dims_per_step": -1 } ``` ### Evaluation Dataset #### Omartificial-Intelligence-Space/arabic-n_li-triplet * Dataset: Omartificial-Intelligence-Space/arabic-n_li-triplet * Size: 6,584 evaluation samples * Columns: anchor, positive, and negative * Approximate statistics based on the first 1000 samples: | | anchor | positive | negative | |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------| | type | string | string | string | | details | | | | * Samples: | anchor | positive | negative | |:-----------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------|:---------------------------------------------------| | امرأتان يتعانقان بينما يحملان حزمة | إمرأتان يحملان حزمة | الرجال يتشاجرون خارج مطعم | | طفلين صغيرين يرتديان قميصاً أزرق، أحدهما يرتدي الرقم 9 والآخر يرتدي الرقم 2 يقفان على خطوات خشبية في الحمام ويغسلان أيديهما في المغسلة. | طفلين يرتديان قميصاً مرقماً يغسلون أيديهم | طفلين يرتديان سترة يذهبان إلى المدرسة | | رجل يبيع الدونات لعميل خلال معرض عالمي أقيم في مدينة أنجليس | رجل يبيع الدونات لعميل | امرأة تشرب قهوتها في مقهى صغير | * Loss: [MatryoshkaLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters: ```json { "loss": "MultipleNegativesRankingLoss", "matryoshka_dims": [ 768, 512, 256, 128, 64 ], "matryoshka_weights": [ 1, 1, 1, 1, 1 ], "n_dims_per_step": -1 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `per_device_train_batch_size`: 64 - `per_device_eval_batch_size`: 64 - `warmup_ratio`: 0.1 - `fp16`: True - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: no - `prediction_loss_only`: True - `per_device_train_batch_size`: 64 - `per_device_eval_batch_size`: 64 - `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`: 5e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 3 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.1 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: True - `save_on_each_node`: False - `save_only_model`: False - `restore_callback_states_from_checkpoint`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `use_ipex`: False - `bf16`: False - `fp16`: True - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: 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`: False - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `dispatch_batches`: None - `split_batches`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `eval_on_start`: False - `eval_use_gather_object`: False - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | sts-test-128_spearman_cosine | sts-test-256_spearman_cosine | sts-test-512_spearman_cosine | sts-test-64_spearman_cosine | sts-test-768_spearman_cosine | |:------:|:-----:|:-------------:|:----------------------------:|:----------------------------:|:----------------------------:|:---------------------------:|:----------------------------:| | 0.0384 | 200 | 9.7813 | - | - | - | - | - | | 0.0768 | 400 | 4.4771 | - | - | - | - | - | | 0.1152 | 600 | 3.754 | - | - | - | - | - | | 0.1536 | 800 | 3.4086 | - | - | - | - | - | | 0.1920 | 1000 | 3.1323 | - | - | - | - | - | | 0.2304 | 1200 | 2.9257 | - | - | - | - | - | | 0.2688 | 1400 | 2.8363 | - | - | - | - | - | | 0.3072 | 1600 | 2.6156 | - | - | - | - | - | | 0.3456 | 1800 | 2.5428 | - | - | - | - | - | | 0.3840 | 2000 | 2.4927 | - | - | - | - | - | | 0.4223 | 2200 | 2.4 | - | - | - | - | - | | 0.4607 | 2400 | 2.3193 | - | - | - | - | - | | 0.4991 | 2600 | 2.2363 | - | - | - | - | - | | 0.5375 | 2800 | 2.1929 | - | - | - | - | - | | 0.5759 | 3000 | 2.1396 | - | - | - | - | - | | 0.6143 | 3200 | 2.0481 | - | - | - | - | - | | 0.6527 | 3400 | 2.0299 | - | - | - | - | - | | 0.6911 | 3600 | 1.9895 | - | - | - | - | - | | 0.7295 | 3800 | 1.9889 | - | - | - | - | - | | 0.7679 | 4000 | 1.9319 | - | - | - | - | - | | 0.8063 | 4200 | 1.8865 | - | - | - | - | - | | 0.8447 | 4400 | 1.8349 | - | - | - | - | - | | 0.8831 | 4600 | 1.8047 | - | - | - | - | - | | 0.9215 | 4800 | 1.8009 | - | - | - | - | - | | 0.9599 | 5000 | 1.7962 | - | - | - | - | - | | 0.9983 | 5200 | 1.7231 | - | - | - | - | - | | 1.0367 | 5400 | 0.0288 | - | - | - | - | - | | 1.0751 | 5600 | 0.0 | - | - | - | - | - | | 1.1135 | 5800 | 0.0 | - | - | - | - | - | | 1.1519 | 6000 | 0.0 | - | - | - | - | - | | 1.1902 | 6200 | 0.0 | - | - | - | - | - | | 1.0056 | 6400 | 0.2935 | - | - | - | - | - | | 1.0440 | 6600 | 1.7571 | - | - | - | - | - | | 1.0824 | 6800 | 1.6487 | - | - | - | - | - | | 1.1208 | 7000 | 1.6513 | - | - | - | - | - | | 1.1591 | 7200 | 1.5466 | - | - | - | - | - | | 1.1975 | 7400 | 1.4583 | - | - | - | - | - | | 1.2359 | 7600 | 1.3805 | - | - | - | - | - | | 1.2743 | 7800 | 1.3264 | - | - | - | - | - | | 1.3127 | 8000 | 1.1898 | - | - | - | - | - | | 1.3511 | 8200 | 1.1961 | - | - | - | - | - | | 1.3895 | 8400 | 1.1749 | - | - | - | - | - | | 1.4279 | 8600 | 1.1438 | - | - | - | - | - | | 1.4663 | 8800 | 1.1481 | - | - | - | - | - | | 1.5047 | 9000 | 1.089 | - | - | - | - | - | | 1.5431 | 9200 | 1.1063 | - | - | - | - | - | | 1.5815 | 9400 | 1.0759 | - | - | - | - | - | | 1.6199 | 9600 | 1.0215 | - | - | - | - | - | | 1.6583 | 9800 | 1.0244 | - | - | - | - | - | | 1.6967 | 10000 | 1.0546 | - | - | - | - | - | | 1.7351 | 10200 | 1.0355 | - | - | - | - | - | | 1.7735 | 10400 | 1.0078 | - | - | - | - | - | | 1.8119 | 10600 | 1.0102 | - | - | - | - | - | | 1.8503 | 10800 | 0.9899 | - | - | - | - | - | | 1.8887 | 11000 | 0.971 | - | - | - | - | - | | 1.9270 | 11200 | 0.9676 | - | - | - | - | - | | 1.9654 | 11400 | 0.9707 | - | - | - | - | - | | 2.0038 | 11600 | 0.8222 | - | - | - | - | - | | 2.0422 | 11800 | 0.0 | - | - | - | - | - | | 2.0806 | 12000 | 0.0 | - | - | - | - | - | | 2.1190 | 12200 | 0.0 | - | - | - | - | - | | 2.1574 | 12400 | 0.0 | - | - | - | - | - | | 2.1958 | 12600 | 0.0 | - | - | - | - | - | | 2.0111 | 12800 | 0.2783 | - | - | - | - | - | | 2.0495 | 13000 | 0.8261 | - | - | - | - | - | | 2.0879 | 13200 | 0.868 | - | - | - | - | - | | 2.1263 | 13400 | 0.8653 | - | - | - | - | - | | 2.1647 | 13600 | 0.8647 | - | - | - | - | - | | 2.2031 | 13800 | 0.8085 | - | - | - | - | - | | 2.2415 | 14000 | 0.8122 | - | - | - | - | - | | 2.2799 | 14200 | 0.7647 | - | - | - | - | - | | 2.3183 | 14400 | 0.6959 | - | - | - | - | - | | 2.3567 | 14600 | 0.7228 | - | - | - | - | - | | 2.3951 | 14800 | 0.7303 | - | - | - | - | - | | 2.4335 | 15000 | 0.7056 | - | - | - | - | - | | 2.4719 | 15200 | 0.737 | - | - | - | - | - | | 2.5103 | 15400 | 0.7016 | - | - | - | - | - | | 2.5487 | 15600 | 0.7183 | - | - | - | - | - | | 2.5538 | 15627 | - | 0.8129 | 0.8138 | 0.8138 | 0.8092 | 0.8140 | ### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.0.1 - Transformers: 4.43.1 - PyTorch: 2.2.2 - Accelerate: 0.33.0 - Datasets: 2.19.0 - 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} } ```