--- language: - en library_name: sentence-transformers tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:67190 - loss:AdaptiveLayerLoss - loss:MultipleNegativesRankingLoss base_model: microsoft/deberta-v3-small datasets: - stanfordnlp/snli metrics: - cosine_accuracy - cosine_accuracy_threshold - cosine_f1 - cosine_f1_threshold - cosine_precision - cosine_recall - cosine_ap - dot_accuracy - dot_accuracy_threshold - dot_f1 - dot_f1_threshold - dot_precision - dot_recall - dot_ap - manhattan_accuracy - manhattan_accuracy_threshold - manhattan_f1 - manhattan_f1_threshold - manhattan_precision - manhattan_recall - manhattan_ap - euclidean_accuracy - euclidean_accuracy_threshold - euclidean_f1 - euclidean_f1_threshold - euclidean_precision - euclidean_recall - euclidean_ap - max_accuracy - max_accuracy_threshold - max_f1 - max_f1_threshold - max_precision - max_recall - max_ap widget: - source_sentence: A person in a red shirt is mowing the grass with a green riding mower. sentences: - A person in red is moving grass on a John Deer motor. - An angry military veteran watches as people protest the war. - A man is sitting on a truck. - source_sentence: Some dogs are running on a deserted beach. sentences: - daddy taught her - There are multiple dogs present. - a woman at a beach - source_sentence: Two street people and a dog sitting on the ground and one is holding an "out of luck" sign. sentences: - A person biking. - The man and woman are married. - the dog is a chihuahua - source_sentence: One tan girl with a wool hat is running and leaning over an object, while another person in a wool hat is sitting on the ground. sentences: - A tan girl runs leans over an object - A man and his daughter are petting a pony. - A man with a baby is petting a pony. - source_sentence: These girls are having a great time looking for seashells. sentences: - The girls are happy. - Two woman are trying to finish orders from a doctor - A girl is standing outside. pipeline_tag: sentence-similarity model-index: - name: SentenceTransformer based on microsoft/deberta-v3-small results: - task: type: binary-classification name: Binary Classification dataset: name: Unknown type: unknown metrics: - type: cosine_accuracy value: 0.6652580742529429 name: Cosine Accuracy - type: cosine_accuracy_threshold value: 0.6691544055938721 name: Cosine Accuracy Threshold - type: cosine_f1 value: 0.7050935184095989 name: Cosine F1 - type: cosine_f1_threshold value: 0.5757889747619629 name: Cosine F1 Threshold - type: cosine_precision value: 0.5903092377388222 name: Cosine Precision - type: cosine_recall value: 0.8752920560747663 name: Cosine Recall - type: cosine_ap value: 0.7023886827641951 name: Cosine Ap - type: dot_accuracy value: 0.6308481738605494 name: Dot Accuracy - type: dot_accuracy_threshold value: 127.05267333984375 name: Dot Accuracy Threshold - type: dot_f1 value: 0.6983614124163396 name: Dot F1 - type: dot_f1_threshold value: 101.77250671386719 name: Dot F1 Threshold - type: dot_precision value: 0.5772605875619993 name: Dot Precision - type: dot_recall value: 0.8837616822429907 name: Dot Recall - type: dot_ap value: 0.6558335483108544 name: Dot Ap - type: manhattan_accuracy value: 0.6675218834892847 name: Manhattan Accuracy - type: manhattan_accuracy_threshold value: 210.99388122558594 name: Manhattan Accuracy Threshold - type: manhattan_f1 value: 0.7107997100748973 name: Manhattan F1 - type: manhattan_f1_threshold value: 252.65306091308594 name: Manhattan F1 Threshold - type: manhattan_precision value: 0.6060980634528225 name: Manhattan Precision - type: manhattan_recall value: 0.8592289719626168 name: Manhattan Recall - type: manhattan_ap value: 0.709424985473672 name: Manhattan Ap - type: euclidean_accuracy value: 0.6619378207063085 name: Euclidean Accuracy - type: euclidean_accuracy_threshold value: 11.227606773376465 name: Euclidean Accuracy Threshold - type: euclidean_f1 value: 0.7073199115559177 name: Euclidean F1 - type: euclidean_f1_threshold value: 12.850802421569824 name: Euclidean F1 Threshold - type: euclidean_precision value: 0.587928032501451 name: Euclidean Precision - type: euclidean_recall value: 0.8875584112149533 name: Euclidean Recall - type: euclidean_ap value: 0.7037559902823934 name: Euclidean Ap - type: max_accuracy value: 0.6675218834892847 name: Max Accuracy - type: max_accuracy_threshold value: 210.99388122558594 name: Max Accuracy Threshold - type: max_f1 value: 0.7107997100748973 name: Max F1 - type: max_f1_threshold value: 252.65306091308594 name: Max F1 Threshold - type: max_precision value: 0.6060980634528225 name: Max Precision - type: max_recall value: 0.8875584112149533 name: Max Recall - type: max_ap value: 0.709424985473672 name: Max Ap --- # SentenceTransformer based on microsoft/deberta-v3-small This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli) 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:** [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 tokens - **Similarity Function:** Cosine Similarity - **Training Dataset:** - [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli) - **Language:** en ### 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: DebertaV2Model (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("bobox/DeBERTaV3-small-ST-AdaptiveLayer-3L-ep2") # Run inference sentences = [ 'These girls are having a great time looking for seashells.', 'The girls are happy.', 'A girl is standing outside.', ] 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 #### Binary Classification * Evaluated with [BinaryClassificationEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator) | Metric | Value | |:-----------------------------|:-----------| | cosine_accuracy | 0.6653 | | cosine_accuracy_threshold | 0.6692 | | cosine_f1 | 0.7051 | | cosine_f1_threshold | 0.5758 | | cosine_precision | 0.5903 | | cosine_recall | 0.8753 | | cosine_ap | 0.7024 | | dot_accuracy | 0.6308 | | dot_accuracy_threshold | 127.0527 | | dot_f1 | 0.6984 | | dot_f1_threshold | 101.7725 | | dot_precision | 0.5773 | | dot_recall | 0.8838 | | dot_ap | 0.6558 | | manhattan_accuracy | 0.6675 | | manhattan_accuracy_threshold | 210.9939 | | manhattan_f1 | 0.7108 | | manhattan_f1_threshold | 252.6531 | | manhattan_precision | 0.6061 | | manhattan_recall | 0.8592 | | manhattan_ap | 0.7094 | | euclidean_accuracy | 0.6619 | | euclidean_accuracy_threshold | 11.2276 | | euclidean_f1 | 0.7073 | | euclidean_f1_threshold | 12.8508 | | euclidean_precision | 0.5879 | | euclidean_recall | 0.8876 | | euclidean_ap | 0.7038 | | max_accuracy | 0.6675 | | max_accuracy_threshold | 210.9939 | | max_f1 | 0.7108 | | max_f1_threshold | 252.6531 | | max_precision | 0.6061 | | max_recall | 0.8876 | | **max_ap** | **0.7094** | ## Training Details ### Training Dataset #### stanfordnlp/snli * Dataset: [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli) at [cdb5c3d](https://huggingface.co/datasets/stanfordnlp/snli/tree/cdb5c3d5eed6ead6e5a341c8e56e669bb666725b) * Size: 67,190 training samples * Columns: sentence1, sentence2, and label * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | label | |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-----------------------------| | type | string | string | int | | details | | | | * Samples: | sentence1 | sentence2 | label | |:---------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------|:---------------| | Without a placebo group, we still won't know if any of the treatments are better than nothing and therefore worth giving. | It is necessary to use a controlled method to ensure the treatments are worthwhile. | 0 | | It was conducted in silence. | It was done silently. | 0 | | oh Lewisville any decent food in your cafeteria up there | Is there any decent food in your cafeteria up there in Lewisville? | 0 | * Loss: [AdaptiveLayerLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#adaptivelayerloss) with these parameters: ```json { "loss": "MultipleNegativesRankingLoss", "n_layers_per_step": 3, "last_layer_weight": 1, "prior_layers_weight": 0.3, "kl_div_weight": 1, "kl_temperature": 1 } ``` ### Evaluation Dataset #### stanfordnlp/snli * Dataset: [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli) at [cdb5c3d](https://huggingface.co/datasets/stanfordnlp/snli/tree/cdb5c3d5eed6ead6e5a341c8e56e669bb666725b) * Size: 6,626 evaluation samples * Columns: premise, hypothesis, and label * Approximate statistics based on the first 1000 samples: | | premise | hypothesis | label | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------| | type | string | string | int | | details | | | | * Samples: | premise | hypothesis | label | |:--------------------------------------------------------------------------------------------------------|:---------------------------------------------------|:---------------| | This church choir sings to the masses as they sing joyous songs from the book at a church. | The church has cracks in the ceiling. | 0 | | This church choir sings to the masses as they sing joyous songs from the book at a church. | The church is filled with song. | 1 | | A woman with a green headscarf, blue shirt and a very big grin. | The woman is young. | 0 | * Loss: [AdaptiveLayerLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#adaptivelayerloss) with these parameters: ```json { "loss": "MultipleNegativesRankingLoss", "n_layers_per_step": 3, "last_layer_weight": 1, "prior_layers_weight": 0.3, "kl_div_weight": 1, "kl_temperature": 1 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 45 - `per_device_eval_batch_size`: 22 - `learning_rate`: 3e-06 - `weight_decay`: 1e-09 - `num_train_epochs`: 2 - `lr_scheduler_type`: cosine - `warmup_ratio`: 0.5 - `save_safetensors`: False - `fp16`: True - `push_to_hub`: True - `hub_model_id`: bobox/DeBERTaV3-small-ST-AdaptiveLayer-3L-ep2-n - `hub_strategy`: checkpoint - `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`: 45 - `per_device_eval_batch_size`: 22 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `eval_accumulation_steps`: None - `learning_rate`: 3e-06 - `weight_decay`: 1e-09 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 2 - `max_steps`: -1 - `lr_scheduler_type`: cosine - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.5 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: False - `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`: True - `resume_from_checkpoint`: None - `hub_model_id`: bobox/DeBERTaV3-small-ST-AdaptiveLayer-3L-ep2-n - `hub_strategy`: checkpoint - `hub_private_repo`: False - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `dispatch_batches`: None - `split_batches`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | loss | max_ap | |:------:|:----:|:-------------:|:------:|:------:| | 0.1004 | 150 | 4.9809 | - | - | | 0.2001 | 299 | - | 3.8956 | 0.6130 | | 0.2008 | 300 | 3.8459 | - | - | | 0.3012 | 450 | 3.1941 | - | - | | 0.4003 | 598 | - | 3.2066 | 0.6526 | | 0.4016 | 600 | 2.7939 | - | - | | 0.5020 | 750 | 2.3082 | - | - | | 0.6004 | 897 | - | 2.4595 | 0.6884 | | 0.6024 | 900 | 1.9658 | - | - | | 0.7028 | 1050 | 1.6975 | - | - | | 0.8005 | 1196 | - | 2.0292 | 0.7010 | | 0.8032 | 1200 | 1.528 | - | - | | 0.9036 | 1350 | 1.3763 | - | - | | 1.0007 | 1495 | - | 1.8192 | 0.7071 | | 1.0040 | 1500 | 1.262 | - | - | | 1.1044 | 1650 | 1.2033 | - | - | | 1.2008 | 1794 | - | 1.6673 | 0.7082 | | 1.2048 | 1800 | 1.1221 | - | - | | 1.3052 | 1950 | 1.0963 | - | - | | 1.4009 | 2093 | - | 1.5816 | 0.7103 | | 1.4056 | 2100 | 1.0742 | - | - | | 1.5060 | 2250 | 1.0242 | - | - | | 1.6011 | 2392 | - | 1.5368 | 0.7094 | | 1.6064 | 2400 | 1.0036 | - | - | | 1.7068 | 2550 | 1.0143 | - | - | | 1.8012 | 2691 | - | 1.5158 | 0.7094 | | 1.8072 | 2700 | 0.9799 | - | - | | 1.9076 | 2850 | 0.9777 | - | - | ### Framework Versions - Python: 3.10.13 - Sentence Transformers: 3.0.1 - Transformers: 4.41.2 - PyTorch: 2.1.2 - Accelerate: 0.30.1 - Datasets: 2.19.2 - 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", } ``` #### AdaptiveLayerLoss ```bibtex @misc{li20242d, title={2D Matryoshka Sentence Embeddings}, author={Xianming Li and Zongxi Li and Jing Li and Haoran Xie and Qing Li}, year={2024}, eprint={2402.14776}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` #### 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} } ```