--- base_model: distilbert/distilbert-base-multilingual-cased 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:654495 - loss:MultipleNegativesRankingLoss widget: - source_sentence: সম্পূৰ্ণৰূপে ভিন্ন ধৰণৰ পেৰাচুট আৰু এটা উড়ন্ত পক্ষীৰ মাজত, আহ্, শব্দৰ তিনিগুণ বেগত, ঘণ্টাৰ ২২, ০০০ মাইলত। sentences: - ঘণ্টাৰ ২০, ০০০ কিলোমিটাৰতকৈ অধিক গতিত উড়ে। - মোৰ ঘৰত দুটা কম্পিউটাৰ আছে। - সকলো ক্ৰীড়াৰ নাম ক্ৰীড়াত ব্যৱহাৰ কৰা এটা সঁজুলিৰ নামেৰে নামকৰণ কৰা হয়। - source_sentence: আৰু তাৰ পিছত মই তেওঁক যাবলৈ শুনিছিলোঁ, সেয়েহে মই এতিয়াও মোৰ কাম শেষ কৰি আছো। sentences: - মই আজি যিটো কৰিব লাগিব সেয়া কৰি আছো। - '"Bato (বা" "vato" ") এটা স্পেনিছ শব্দ যাৰ অৰ্থ হৈছে" "পুৰুষ" "বা" "বন্ধু" "।"' - পিতৃ-মাতৃয়ে ঘৰত থাকিল। - source_sentence: মই কেৱল বুজাবলৈ চেষ্টা কৰিছিলোঁ। sentences: - মই বুজিবলৈ চেষ্টা কৰিছিলোঁ। - মই আন কেইবাটাও প্ৰস্তাৱ দিবলৈ আহিছিলোঁ। - প্ৰেমিক নামৰ এজন খেতিয়কে নিজৰ হত্যাৰ আঁচনি তৈয়াৰ কৰোতে ঘাসপূৰ্ণ স্থানত লুকুৱাই থৈ যায়। - source_sentence: আৰু, উম, যদি এইটো বাঢ়ি আহিব আৰু কেৱল বাঢ়ি আহিব তেতিয়াহ 'লে' whish 'হ' ব, আৰু যেনেকৈ ই আপোনাৰ মূৰটো বন্ধ কৰি দিব। sentences: - প্ৰাৰম্ভিক শিক্ষা লাভ কৰা আৰু বয়সস্থ ল 'ৰা-ছোৱালীয়ে প্ৰায়ে ভৱিষ্যতৰ বিষয়ে সপোন দেখে। - তেওঁলোকে মোৰ ওচৰলৈ কিয় আহিছে বুলি প্ৰশ্ন কৰিলে। - যদি কোনো ধৰণৰ পৰিৱৰ্তন হয়, তেনেহ 'লে তাৰ লগত এক শব্দ বাঢ়িব পাৰে। - source_sentence: মই ভালদৰে জানিব নোৱাৰোঁ আপোনালোকৰ সৈতে কথা বতৰা আৰু এক ভাল সন্ধ্যা আছিল sentences: - মই নিশ্চিত নহয় কিন্তু মই অলপ ভাল, আজি ৰাতি আপোনালোকৰ সৈতে কথা পাতিবলৈ পাই ভাল লাগিল। - Shannon এ বাৰ্তা উপেক্ষা কৰিছে। - মানুহজনে ষ্টক এক্সচেঞ্জত লেনদেনৰ বিষয়ে জানিবলৈ চেষ্টা কৰিছিল। model-index: - name: SentenceTransformer based on distilbert/distilbert-base-multilingual-cased results: - task: type: semantic-similarity name: Semantic Similarity dataset: name: pritamdeka/stsb assamese translated dev type: pritamdeka/stsb-assamese-translated-dev metrics: - type: pearson_cosine value: 0.7169579983340281 name: Pearson Cosine - type: spearman_cosine value: 0.7220987460972806 name: Spearman Cosine - type: pearson_manhattan value: 0.7380110422340219 name: Pearson Manhattan - type: spearman_manhattan value: 0.7452082040848071 name: Spearman Manhattan - type: pearson_euclidean value: 0.7386577662108481 name: Pearson Euclidean - type: spearman_euclidean value: 0.7458961406429292 name: Spearman Euclidean - type: pearson_dot value: 0.6480820840127198 name: Pearson Dot - type: spearman_dot value: 0.6478256799308721 name: Spearman Dot - type: pearson_max value: 0.7386577662108481 name: Pearson Max - type: spearman_max value: 0.7458961406429292 name: Spearman Max - task: type: semantic-similarity name: Semantic Similarity dataset: name: pritamdeka/stsb assamese translated test type: pritamdeka/stsb-assamese-translated-test metrics: - type: pearson_cosine value: 0.656822131496386 name: Pearson Cosine - type: spearman_cosine value: 0.6621886312595516 name: Spearman Cosine - type: pearson_manhattan value: 0.6675496858061083 name: Pearson Manhattan - type: spearman_manhattan value: 0.6722470705036974 name: Spearman Manhattan - type: pearson_euclidean value: 0.6681862838868354 name: Pearson Euclidean - type: spearman_euclidean value: 0.6727345795749732 name: Spearman Euclidean - type: pearson_dot value: 0.5691955650489428 name: Pearson Dot - type: spearman_dot value: 0.570867962692759 name: Spearman Dot - type: pearson_max value: 0.6681862838868354 name: Pearson Max - type: spearman_max value: 0.6727345795749732 name: Spearman Max --- # SentenceTransformer based on distilbert/distilbert-base-multilingual-cased This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased). 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:** [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased) - **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: DistilBertModel (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("pritamdeka/distilbert-base-multilingual-cased-indicxnli-random-negatives-v1") # Run inference sentences = [ 'মই ভালদৰে জানিব নোৱাৰোঁ আপোনালোকৰ সৈতে কথা বতৰা আৰু এক ভাল সন্ধ্যা আছিল', 'মই নিশ্চিত নহয় কিন্তু মই অলপ ভাল, আজি ৰাতি আপোনালোকৰ সৈতে কথা পাতিবলৈ পাই ভাল লাগিল।', 'Shannon এ বাৰ্তা উপেক্ষা কৰিছে।', ] 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: `pritamdeka/stsb-assamese-translated-dev` * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.717 | | **spearman_cosine** | **0.7221** | | pearson_manhattan | 0.738 | | spearman_manhattan | 0.7452 | | pearson_euclidean | 0.7387 | | spearman_euclidean | 0.7459 | | pearson_dot | 0.6481 | | spearman_dot | 0.6478 | | pearson_max | 0.7387 | | spearman_max | 0.7459 | #### Semantic Similarity * Dataset: `pritamdeka/stsb-assamese-translated-test` * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.6568 | | **spearman_cosine** | **0.6622** | | pearson_manhattan | 0.6675 | | spearman_manhattan | 0.6722 | | pearson_euclidean | 0.6682 | | spearman_euclidean | 0.6727 | | pearson_dot | 0.5692 | | spearman_dot | 0.5709 | | pearson_max | 0.6682 | | spearman_max | 0.6727 | ## Training Details ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 64 - `per_device_eval_batch_size`: 64 - `num_train_epochs`: 1 - `warmup_ratio`: 0.1 - `fp16`: True - `load_best_model_at_end`: True - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `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 - `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`: 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 - `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`: 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 - `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 - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | loss | pritamdeka/stsb-assamese-translated-dev_spearman_cosine | pritamdeka/stsb-assamese-translated-test_spearman_cosine | |:----------:|:---------:|:-------------:|:----------:|:-------------------------------------------------------:|:--------------------------------------------------------:| | 0 | 0 | - | - | 0.5489 | - | | 0.0489 | 500 | 1.9387 | 1.7308 | 0.6808 | - | | 0.0978 | 1000 | 1.0503 | 1.7373 | 0.6689 | - | | 0.1467 | 1500 | 0.92 | 1.5838 | 0.6761 | - | | 0.1956 | 2000 | 0.8754 | 1.4807 | 0.6518 | - | | 0.2445 | 2500 | 0.7988 | 1.3797 | 0.6853 | - | | 0.2933 | 3000 | 0.7606 | 1.3713 | 0.7108 | - | | 0.3422 | 3500 | 0.7228 | 1.2510 | 0.6677 | - | | 0.3911 | 4000 | 0.688 | 1.2374 | 0.6734 | - | | 0.4400 | 4500 | 0.6992 | 1.2173 | 0.6891 | - | | 0.4889 | 5000 | 0.6108 | 1.1638 | 0.7017 | - | | 0.5378 | 5500 | 0.612 | 1.0815 | 0.7102 | - | | 0.5867 | 6000 | 0.6259 | 1.0664 | 0.7202 | - | | 0.6356 | 6500 | 0.5863 | 1.0464 | 0.7047 | - | | 0.6845 | 7000 | 0.5941 | 1.0111 | 0.7101 | - | | 0.7334 | 7500 | 0.5436 | 1.0023 | 0.7171 | - | | 0.7822 | 8000 | 0.555 | 0.9633 | 0.7202 | - | | 0.8311 | 8500 | 0.5466 | 0.9651 | 0.7279 | - | | 0.8800 | 9000 | 0.5326 | 0.9611 | 0.7262 | - | | 0.9289 | 9500 | 0.5055 | 0.9313 | 0.7276 | - | | **0.9778** | **10000** | **0.4828** | **0.9172** | **0.7221** | **-** | | 1.0 | 10227 | - | - | - | 0.6622 | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.0.1 - Transformers: 4.42.4 - PyTorch: 2.3.1+cu121 - Accelerate: 0.32.1 - Datasets: 2.20.0 - 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", } ``` #### 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} } ```