--- language: [] library_name: sentence-transformers tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:557850 - loss:MatryoshkaLoss - loss:MultipleNegativesRankingLoss base_model: UBC-NLP/serengeti-E250 datasets: [] metrics: - pearson_cosine - spearman_cosine - pearson_manhattan - spearman_manhattan - pearson_euclidean - spearman_euclidean - pearson_dot - spearman_dot - pearson_max - spearman_max widget: - source_sentence: Mwanamume aliyepangwa vizuri anasimama kwa mguu mmoja karibu na pwani safi ya bahari. sentences: - mtu anacheka wakati wa kufua nguo - Mwanamume fulani yuko nje karibu na ufuo wa bahari. - Mwanamume fulani ameketi kwenye sofa yake. - source_sentence: Mwanamume mwenye ngozi nyeusi akivuta sigareti karibu na chombo cha taka cha kijani. sentences: - Karibu na chombo cha taka mwanamume huyo alisimama na kuvuta sigareti - Kitanda ni chafu. - Alipokuwa kwenye dimbwi la kuogelea mvulana huyo mwenye ugonjwa wa albino alijihadhari na jua kupita kiasi - source_sentence: Mwanamume kijana mwenye nywele nyekundu anaketi ukutani akisoma gazeti huku mwanamke na msichana mchanga wakipita. sentences: - Mwanamume aliyevalia shati la bluu amegonga ukuta kando ya barabara na gari la bluu na gari nyekundu lenye maji nyuma. - Mwanamume mchanga anatazama gazeti huku wanawake wawili wakipita karibu naye. - Mwanamume huyo mchanga analala huku Mama akimwongoza binti yake kwenye bustani. - source_sentence: Wasichana wako nje. sentences: - Wasichana wawili wakisafiri kwenye sehemu ya kusisimua. - Kuna watu watatu wakiongoza gari linaloweza kugeuzwa-geuzwa wakipita watu wengine. - Wasichana watatu wamesimama pamoja katika chumba, mmoja anasikiliza, mwingine anaandika ukutani na wa tatu anaongea nao. - source_sentence: Mwanamume aliyevalia koti la bluu la kuzuia upepo, amelala uso chini kwenye benchi ya bustani, akiwa na chupa ya pombe iliyofungwa kwenye mojawapo ya miguu ya benchi. sentences: - Mwanamume amelala uso chini kwenye benchi ya bustani. - Mwanamke anaunganisha uzi katika mipira kando ya rundo la mipira - Mwanamume fulani anacheza dansi kwenye klabu hiyo akifungua chupa. pipeline_tag: sentence-similarity model-index: - name: SentenceTransformer based on UBC-NLP/serengeti-E250 results: - task: type: semantic-similarity name: Semantic Similarity dataset: name: sts test 768 type: sts-test-768 metrics: - type: pearson_cosine value: 0.7113368462970326 name: Pearson Cosine - type: spearman_cosine value: 0.706531149090894 name: Spearman Cosine - type: pearson_manhattan value: 0.7134349154531519 name: Pearson Manhattan - type: spearman_manhattan value: 0.7023005843725415 name: Spearman Manhattan - type: pearson_euclidean value: 0.7137962920501839 name: Pearson Euclidean - type: spearman_euclidean value: 0.7020941994285994 name: Spearman Euclidean - type: pearson_dot value: 0.3920803758314358 name: Pearson Dot - type: spearman_dot value: 0.3601086266312748 name: Spearman Dot - type: pearson_max value: 0.7137962920501839 name: Pearson Max - type: spearman_max value: 0.706531149090894 name: Spearman Max - task: type: semantic-similarity name: Semantic Similarity dataset: name: sts test 512 type: sts-test-512 metrics: - type: pearson_cosine value: 0.7090618585285485 name: Pearson Cosine - type: spearman_cosine value: 0.7045766195278508 name: Spearman Cosine - type: pearson_manhattan value: 0.7129955390384859 name: Pearson Manhattan - type: spearman_manhattan value: 0.7021695501159393 name: Spearman Manhattan - type: pearson_euclidean value: 0.7138697740168334 name: Pearson Euclidean - type: spearman_euclidean value: 0.7032055408694606 name: Spearman Euclidean - type: pearson_dot value: 0.39352767760073326 name: Pearson Dot - type: spearman_dot value: 0.3628376619678567 name: Spearman Dot - type: pearson_max value: 0.7138697740168334 name: Pearson Max - type: spearman_max value: 0.7045766195278508 name: Spearman Max - task: type: semantic-similarity name: Semantic Similarity dataset: name: sts test 256 type: sts-test-256 metrics: - type: pearson_cosine value: 0.7067837420770313 name: Pearson Cosine - type: spearman_cosine value: 0.7044452613349608 name: Spearman Cosine - type: pearson_manhattan value: 0.7137425083925593 name: Pearson Manhattan - type: spearman_manhattan value: 0.7032345257234871 name: Spearman Manhattan - type: pearson_euclidean value: 0.7146861583047366 name: Pearson Euclidean - type: spearman_euclidean value: 0.7039212190752775 name: Spearman Euclidean - type: pearson_dot value: 0.37462153895392747 name: Pearson Dot - type: spearman_dot value: 0.34441190254194326 name: Spearman Dot - type: pearson_max value: 0.7146861583047366 name: Pearson Max - type: spearman_max value: 0.7044452613349608 name: Spearman Max - task: type: semantic-similarity name: Semantic Similarity dataset: name: sts test 128 type: sts-test-128 metrics: - type: pearson_cosine value: 0.7046839100746249 name: Pearson Cosine - type: spearman_cosine value: 0.7050559450173808 name: Spearman Cosine - type: pearson_manhattan value: 0.7120431790616113 name: Pearson Manhattan - type: spearman_manhattan value: 0.7010054121016321 name: Spearman Manhattan - type: pearson_euclidean value: 0.7132280398983044 name: Pearson Euclidean - type: spearman_euclidean value: 0.701626975970973 name: Spearman Euclidean - type: pearson_dot value: 0.35455409787695585 name: Pearson Dot - type: spearman_dot value: 0.32292034736383524 name: Spearman Dot - type: pearson_max value: 0.7132280398983044 name: Pearson Max - type: spearman_max value: 0.7050559450173808 name: Spearman Max - task: type: semantic-similarity name: Semantic Similarity dataset: name: sts test 64 type: sts-test-64 metrics: - type: pearson_cosine value: 0.7012310578605567 name: Pearson Cosine - type: spearman_cosine value: 0.7044132231714119 name: Spearman Cosine - type: pearson_manhattan value: 0.7091211798265005 name: Pearson Manhattan - type: spearman_manhattan value: 0.6972792688781575 name: Spearman Manhattan - type: pearson_euclidean value: 0.7103033981031003 name: Pearson Euclidean - type: spearman_euclidean value: 0.6985716335223231 name: Spearman Euclidean - type: pearson_dot value: 0.3379821887901175 name: Pearson Dot - type: spearman_dot value: 0.30513652558145304 name: Spearman Dot - type: pearson_max value: 0.7103033981031003 name: Pearson Max - type: spearman_max value: 0.7044132231714119 name: Spearman Max --- # SentenceTransformer based on UBC-NLP/serengeti-E250 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [UBC-NLP/serengeti-E250](https://huggingface.co/UBC-NLP/serengeti-E250). 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:** [UBC-NLP/serengeti-E250](https://huggingface.co/UBC-NLP/serengeti-E250) - **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: ElectraModel (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("Mollel/swahili-serengeti-E250-nli-matryoshka") # Run inference sentences = [ 'Mwanamume aliyevalia koti la bluu la kuzuia upepo, amelala uso chini kwenye benchi ya bustani, akiwa na chupa ya pombe iliyofungwa kwenye mojawapo ya miguu ya benchi.', 'Mwanamume amelala uso chini kwenye benchi ya bustani.', 'Mwanamume fulani anacheza dansi kwenye klabu hiyo akifungua chupa.', ] 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 | 0.7113 | | **spearman_cosine** | **0.7065** | | pearson_manhattan | 0.7134 | | spearman_manhattan | 0.7023 | | pearson_euclidean | 0.7138 | | spearman_euclidean | 0.7021 | | pearson_dot | 0.3921 | | spearman_dot | 0.3601 | | pearson_max | 0.7138 | | spearman_max | 0.7065 | #### 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 | 0.7091 | | **spearman_cosine** | **0.7046** | | pearson_manhattan | 0.713 | | spearman_manhattan | 0.7022 | | pearson_euclidean | 0.7139 | | spearman_euclidean | 0.7032 | | pearson_dot | 0.3935 | | spearman_dot | 0.3628 | | pearson_max | 0.7139 | | spearman_max | 0.7046 | #### 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 | 0.7068 | | **spearman_cosine** | **0.7044** | | pearson_manhattan | 0.7137 | | spearman_manhattan | 0.7032 | | pearson_euclidean | 0.7147 | | spearman_euclidean | 0.7039 | | pearson_dot | 0.3746 | | spearman_dot | 0.3444 | | pearson_max | 0.7147 | | spearman_max | 0.7044 | #### 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 | 0.7047 | | **spearman_cosine** | **0.7051** | | pearson_manhattan | 0.712 | | spearman_manhattan | 0.701 | | pearson_euclidean | 0.7132 | | spearman_euclidean | 0.7016 | | pearson_dot | 0.3546 | | spearman_dot | 0.3229 | | pearson_max | 0.7132 | | spearman_max | 0.7051 | #### 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 | 0.7012 | | **spearman_cosine** | **0.7044** | | pearson_manhattan | 0.7091 | | spearman_manhattan | 0.6973 | | pearson_euclidean | 0.7103 | | spearman_euclidean | 0.6986 | | pearson_dot | 0.338 | | spearman_dot | 0.3051 | | pearson_max | 0.7103 | | spearman_max | 0.7044 | ## Training Details ### Training Hyperparameters #### Non-Default Hyperparameters - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `learning_rate`: 2e-05 - `num_train_epochs`: 1 - `warmup_ratio`: 0.1 - `bf16`: True - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `prediction_loss_only`: True - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `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`: 1 - `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 - `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, '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_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional
### Training Logs
Click to expand | 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 | |:------:|:-----:|:-------------:|:----------------------------:|:----------------------------:|:----------------------------:|:---------------------------:|:----------------------------:| | 0.0057 | 100 | 25.7713 | - | - | - | - | - | | 0.0115 | 200 | 20.7886 | - | - | - | - | - | | 0.0172 | 300 | 17.0398 | - | - | - | - | - | | 0.0229 | 400 | 15.3913 | - | - | - | - | - | | 0.0287 | 500 | 14.0214 | - | - | - | - | - | | 0.0344 | 600 | 12.2125 | - | - | - | - | - | | 0.0402 | 700 | 10.3033 | - | - | - | - | - | | 0.0459 | 800 | 9.3822 | - | - | - | - | - | | 0.0516 | 900 | 8.9276 | - | - | - | - | - | | 0.0574 | 1000 | 8.552 | - | - | - | - | - | | 0.0631 | 1100 | 8.6293 | - | - | - | - | - | | 0.0688 | 1200 | 8.5353 | - | - | - | - | - | | 0.0746 | 1300 | 8.6431 | - | - | - | - | - | | 0.0803 | 1400 | 8.3192 | - | - | - | - | - | | 0.0860 | 1500 | 7.1834 | - | - | - | - | - | | 0.0918 | 1600 | 6.7834 | - | - | - | - | - | | 0.0975 | 1700 | 6.4758 | - | - | - | - | - | | 0.1033 | 1800 | 6.756 | - | - | - | - | - | | 0.1090 | 1900 | 7.807 | - | - | - | - | - | | 0.1147 | 2000 | 6.8836 | - | - | - | - | - | | 0.1205 | 2100 | 6.9948 | - | - | - | - | - | | 0.1262 | 2200 | 6.5031 | - | - | - | - | - | | 0.1319 | 2300 | 6.3596 | - | - | - | - | - | | 0.1377 | 2400 | 6.0257 | - | - | - | - | - | | 0.1434 | 2500 | 5.9757 | - | - | - | - | - | | 0.1491 | 2600 | 5.464 | - | - | - | - | - | | 0.1549 | 2700 | 5.6518 | - | - | - | - | - | | 0.1606 | 2800 | 6.2899 | - | - | - | - | - | | 0.1664 | 2900 | 6.4876 | - | - | - | - | - | | 0.1721 | 3000 | 6.9466 | - | - | - | - | - | | 0.1778 | 3100 | 6.8439 | - | - | - | - | - | | 0.1836 | 3200 | 6.2545 | - | - | - | - | - | | 0.1893 | 3300 | 5.9795 | - | - | - | - | - | | 0.1950 | 3400 | 5.3904 | - | - | - | - | - | | 0.2008 | 3500 | 6.2798 | - | - | - | - | - | | 0.2065 | 3600 | 5.6882 | - | - | - | - | - | | 0.2122 | 3700 | 6.195 | - | - | - | - | - | | 0.2180 | 3800 | 5.8728 | - | - | - | - | - | | 0.2237 | 3900 | 6.2428 | - | - | - | - | - | | 0.2294 | 4000 | 5.801 | - | - | - | - | - | | 0.2352 | 4100 | 5.6918 | - | - | - | - | - | | 0.2409 | 4200 | 5.3977 | - | - | - | - | - | | 0.2467 | 4300 | 5.8792 | - | - | - | - | - | | 0.2524 | 4400 | 5.9297 | - | - | - | - | - | | 0.2581 | 4500 | 6.161 | - | - | - | - | - | | 0.2639 | 4600 | 5.6571 | - | - | - | - | - | | 0.2696 | 4700 | 5.5849 | - | - | - | - | - | | 0.2753 | 4800 | 5.6382 | - | - | - | - | - | | 0.2811 | 4900 | 5.2978 | - | - | - | - | - | | 0.2868 | 5000 | 5.108 | - | - | - | - | - | | 0.2925 | 5100 | 5.1158 | - | - | - | - | - | | 0.2983 | 5200 | 5.6218 | - | - | - | - | - | | 0.3040 | 5300 | 5.643 | - | - | - | - | - | | 0.3098 | 5400 | 5.6894 | - | - | - | - | - | | 0.3155 | 5500 | 5.373 | - | - | - | - | - | | 0.3212 | 5600 | 5.0673 | - | - | - | - | - | | 0.3270 | 5700 | 5.1915 | - | - | - | - | - | | 0.3327 | 5800 | 5.3705 | - | - | - | - | - | | 0.3384 | 5900 | 5.6432 | - | - | - | - | - | | 0.3442 | 6000 | 5.2567 | - | - | - | - | - | | 0.3499 | 6100 | 5.4516 | - | - | - | - | - | | 0.3556 | 6200 | 5.4844 | - | - | - | - | - | | 0.3614 | 6300 | 4.8238 | - | - | - | - | - | | 0.3671 | 6400 | 4.8271 | - | - | - | - | - | | 0.3729 | 6500 | 4.9863 | - | - | - | - | - | | 0.3786 | 6600 | 5.4894 | - | - | - | - | - | | 0.3843 | 6700 | 4.95 | - | - | - | - | - | | 0.3901 | 6800 | 5.0881 | - | - | - | - | - | | 0.3958 | 6900 | 5.249 | - | - | - | - | - | | 0.4015 | 7000 | 5.0082 | - | - | - | - | - | | 0.4073 | 7100 | 5.5064 | - | - | - | - | - | | 0.4130 | 7200 | 5.0885 | - | - | - | - | - | | 0.4187 | 7300 | 5.0321 | - | - | - | - | - | | 0.4245 | 7400 | 4.8212 | - | - | - | - | - | | 0.4302 | 7500 | 5.4231 | - | - | - | - | - | | 0.4360 | 7600 | 4.7687 | - | - | - | - | - | | 0.4417 | 7700 | 4.5707 | - | - | - | - | - | | 0.4474 | 7800 | 5.2229 | - | - | - | - | - | | 0.4532 | 7900 | 5.2446 | - | - | - | - | - | | 0.4589 | 8000 | 4.682 | - | - | - | - | - | | 0.4646 | 8100 | 4.888 | - | - | - | - | - | | 0.4704 | 8200 | 5.0496 | - | - | - | - | - | | 0.4761 | 8300 | 4.7089 | - | - | - | - | - | | 0.4818 | 8400 | 4.9567 | - | - | - | - | - | | 0.4876 | 8500 | 4.7913 | - | - | - | - | - | | 0.4933 | 8600 | 4.8904 | - | - | - | - | - | | 0.4991 | 8700 | 5.247 | - | - | - | - | - | | 0.5048 | 8800 | 4.8254 | - | - | - | - | - | | 0.5105 | 8900 | 4.973 | - | - | - | - | - | | 0.5163 | 9000 | 4.6657 | - | - | - | - | - | | 0.5220 | 9100 | 4.9224 | - | - | - | - | - | | 0.5277 | 9200 | 4.8163 | - | - | - | - | - | | 0.5335 | 9300 | 4.3673 | - | - | - | - | - | | 0.5392 | 9400 | 4.6509 | - | - | - | - | - | | 0.5449 | 9500 | 5.0667 | - | - | - | - | - | | 0.5507 | 9600 | 4.8771 | - | - | - | - | - | | 0.5564 | 9700 | 5.1056 | - | - | - | - | - | | 0.5622 | 9800 | 4.8297 | - | - | - | - | - | | 0.5679 | 9900 | 5.0156 | - | - | - | - | - | | 0.5736 | 10000 | 5.0758 | - | - | - | - | - | | 0.5794 | 10100 | 4.9551 | - | - | - | - | - | | 0.5851 | 10200 | 4.9594 | - | - | - | - | - | | 0.5908 | 10300 | 5.136 | - | - | - | - | - | | 0.5966 | 10400 | 4.7873 | - | - | - | - | - | | 0.6023 | 10500 | 4.5154 | - | - | - | - | - | | 0.6080 | 10600 | 4.928 | - | - | - | - | - | | 0.6138 | 10700 | 5.1825 | - | - | - | - | - | | 0.6195 | 10800 | 5.046 | - | - | - | - | - | | 0.6253 | 10900 | 5.0111 | - | - | - | - | - | | 0.6310 | 11000 | 4.9458 | - | - | - | - | - | | 0.6367 | 11100 | 5.188 | - | - | - | - | - | | 0.6425 | 11200 | 4.6219 | - | - | - | - | - | | 0.6482 | 11300 | 5.3367 | - | - | - | - | - | | 0.6539 | 11400 | 4.9851 | - | - | - | - | - | | 0.6597 | 11500 | 5.2068 | - | - | - | - | - | | 0.6654 | 11600 | 4.3789 | - | - | - | - | - | | 0.6711 | 11700 | 5.3533 | - | - | - | - | - | | 0.6769 | 11800 | 5.3983 | - | - | - | - | - | | 0.6826 | 11900 | 4.6 | - | - | - | - | - | | 0.6883 | 12000 | 4.6668 | - | - | - | - | - | | 0.6941 | 12100 | 5.0814 | - | - | - | - | - | | 0.6998 | 12200 | 5.0787 | - | - | - | - | - | | 0.7056 | 12300 | 4.6325 | - | - | - | - | - | | 0.7113 | 12400 | 4.9415 | - | - | - | - | - | | 0.7170 | 12500 | 4.7053 | - | - | - | - | - | | 0.7228 | 12600 | 4.3212 | - | - | - | - | - | | 0.7285 | 12700 | 4.8205 | - | - | - | - | - | | 0.7342 | 12800 | 4.8602 | - | - | - | - | - | | 0.7400 | 12900 | 4.6944 | - | - | - | - | - | | 0.7457 | 13000 | 4.7785 | - | - | - | - | - | | 0.7514 | 13100 | 4.3515 | - | - | - | - | - | | 0.7572 | 13200 | 5.7561 | - | - | - | - | - | | 0.7629 | 13300 | 5.3526 | - | - | - | - | - | | 0.7687 | 13400 | 5.187 | - | - | - | - | - | | 0.7744 | 13500 | 5.0143 | - | - | - | - | - | | 0.7801 | 13600 | 4.515 | - | - | - | - | - | | 0.7859 | 13700 | 4.639 | - | - | - | - | - | | 0.7916 | 13800 | 4.5556 | - | - | - | - | - | | 0.7973 | 13900 | 4.3526 | - | - | - | - | - | | 0.8031 | 14000 | 4.3091 | - | - | - | - | - | | 0.8088 | 14100 | 4.1761 | - | - | - | - | - | | 0.8145 | 14200 | 4.0484 | - | - | - | - | - | | 0.8203 | 14300 | 4.1886 | - | - | - | - | - | | 0.8260 | 14400 | 4.237 | - | - | - | - | - | | 0.8318 | 14500 | 4.2167 | - | - | - | - | - | | 0.8375 | 14600 | 4.0329 | - | - | - | - | - | | 0.8432 | 14700 | 3.9902 | - | - | - | - | - | | 0.8490 | 14800 | 3.8211 | - | - | - | - | - | | 0.8547 | 14900 | 4.0048 | - | - | - | - | - | | 0.8604 | 15000 | 3.7979 | - | - | - | - | - | | 0.8662 | 15100 | 3.8117 | - | - | - | - | - | | 0.8719 | 15200 | 3.909 | - | - | - | - | - | | 0.8776 | 15300 | 3.8526 | - | - | - | - | - | | 0.8834 | 15400 | 3.79 | - | - | - | - | - | | 0.8891 | 15500 | 3.7792 | - | - | - | - | - | | 0.8949 | 15600 | 3.7469 | - | - | - | - | - | | 0.9006 | 15700 | 3.8387 | - | - | - | - | - | | 0.9063 | 15800 | 3.6418 | - | - | - | - | - | | 0.9121 | 15900 | 3.645 | - | - | - | - | - | | 0.9178 | 16000 | 3.4861 | - | - | - | - | - | | 0.9235 | 16100 | 3.6416 | - | - | - | - | - | | 0.9293 | 16200 | 3.6665 | - | - | - | - | - | | 0.9350 | 16300 | 3.6809 | - | - | - | - | - | | 0.9407 | 16400 | 3.7944 | - | - | - | - | - | | 0.9465 | 16500 | 3.6585 | - | - | - | - | - | | 0.9522 | 16600 | 3.5398 | - | - | - | - | - | | 0.9580 | 16700 | 3.7036 | - | - | - | - | - | | 0.9637 | 16800 | 3.6386 | - | - | - | - | - | | 0.9694 | 16900 | 3.5501 | - | - | - | - | - | | 0.9752 | 17000 | 3.7957 | - | - | - | - | - | | 0.9809 | 17100 | 3.6076 | - | - | - | - | - | | 0.9866 | 17200 | 3.4653 | - | - | - | - | - | | 0.9924 | 17300 | 3.6768 | - | - | - | - | - | | 0.9981 | 17400 | 3.49 | - | - | - | - | - | | 1.0 | 17433 | - | 0.7051 | 0.7044 | 0.7046 | 0.7044 | 0.7065 |
### Framework Versions - Python: 3.11.9 - Sentence Transformers: 3.0.1 - Transformers: 4.40.1 - PyTorch: 2.3.0+cu121 - Accelerate: 0.29.3 - 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} } ```