--- base_model: BXresearch/DeBERTa2-0.9B-ST-v2 datasets: - sentence-transformers/stsb language: - en 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 - 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 pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:5749 - loss:AnglELoss widget: - source_sentence: Left side of a silver train engine. sentences: - A close-up of a black train engine. - Two boys are in midair jumping into an inground pool. - An older Asian couple poses with a newborn baby at the dinner table. - source_sentence: Four girls in swimsuits are playing volleyball at the beach. sentences: - A little girl is walking down a hallway. - The man is erasing the chalk board. - Four women in bikinis are playing volleyball on the beach. - source_sentence: A woman is cooking meat. sentences: - The dogs are alone in the forest. - A man is speaking. - A dog jumps through a hoop. - source_sentence: A person is folding a square paper piece. sentences: - A woman is carrying her baby. - A person folds a piece of paper. - A dog is trying to get through his dog door. - source_sentence: The boy is playing the piano. sentences: - The woman is pouring oil into the pan. - A small black and white dog is swimming in water. - Two brown dogs are playing with each other in the snow. model-index: - name: SentenceTransformer based on BXresearch/DeBERTa2-0.9B-ST-v2 results: - task: type: semantic-similarity name: Semantic Similarity dataset: name: sts test type: sts-test metrics: - type: pearson_cosine value: 0.9174070307741418 name: Pearson Cosine - type: spearman_cosine value: 0.9292509717696739 name: Spearman Cosine - type: pearson_manhattan value: 0.9282688885676256 name: Pearson Manhattan - type: spearman_manhattan value: 0.9298350652202988 name: Spearman Manhattan - type: pearson_euclidean value: 0.9286763713344532 name: Pearson Euclidean - type: spearman_euclidean value: 0.9301882421673056 name: Spearman Euclidean - type: pearson_dot value: 0.9015673628485675 name: Pearson Dot - type: spearman_dot value: 0.9062672614479156 name: Spearman Dot - type: pearson_max value: 0.9286763713344532 name: Pearson Max - type: spearman_max value: 0.9301882421673056 name: Spearman Max - task: type: binary-classification name: Binary Classification dataset: name: allNLI dev type: allNLI-dev metrics: - type: cosine_accuracy value: 0.75390625 name: Cosine Accuracy - type: cosine_accuracy_threshold value: 0.7934484481811523 name: Cosine Accuracy Threshold - type: cosine_f1 value: 0.6263736263736264 name: Cosine F1 - type: cosine_f1_threshold value: 0.7287859916687012 name: Cosine F1 Threshold - type: cosine_precision value: 0.5643564356435643 name: Cosine Precision - type: cosine_recall value: 0.7037037037037037 name: Cosine Recall - type: cosine_ap value: 0.5952488621962656 name: Cosine Ap - type: dot_accuracy value: 0.74609375 name: Dot Accuracy - type: dot_accuracy_threshold value: 853.7699584960938 name: Dot Accuracy Threshold - type: dot_f1 value: 0.6106194690265486 name: Dot F1 - type: dot_f1_threshold value: 685.536865234375 name: Dot F1 Threshold - type: dot_precision value: 0.47586206896551725 name: Dot Precision - type: dot_recall value: 0.8518518518518519 name: Dot Recall - type: dot_ap value: 0.5773093883122924 name: Dot Ap - type: manhattan_accuracy value: 0.75390625 name: Manhattan Accuracy - type: manhattan_accuracy_threshold value: 654.8433227539062 name: Manhattan Accuracy Threshold - type: manhattan_f1 value: 0.6244343891402715 name: Manhattan F1 - type: manhattan_f1_threshold value: 811.658203125 name: Manhattan F1 Threshold - type: manhattan_precision value: 0.4928571428571429 name: Manhattan Precision - type: manhattan_recall value: 0.8518518518518519 name: Manhattan Recall - type: manhattan_ap value: 0.596555546112473 name: Manhattan Ap - type: euclidean_accuracy value: 0.75390625 name: Euclidean Accuracy - type: euclidean_accuracy_threshold value: 21.04879379272461 name: Euclidean Accuracy Threshold - type: euclidean_f1 value: 0.6244343891402715 name: Euclidean F1 - type: euclidean_f1_threshold value: 26.11341094970703 name: Euclidean F1 Threshold - type: euclidean_precision value: 0.4928571428571429 name: Euclidean Precision - type: euclidean_recall value: 0.8518518518518519 name: Euclidean Recall - type: euclidean_ap value: 0.595001077180561 name: Euclidean Ap - type: max_accuracy value: 0.75390625 name: Max Accuracy - type: max_accuracy_threshold value: 853.7699584960938 name: Max Accuracy Threshold - type: max_f1 value: 0.6263736263736264 name: Max F1 - type: max_f1_threshold value: 811.658203125 name: Max F1 Threshold - type: max_precision value: 0.5643564356435643 name: Max Precision - type: max_recall value: 0.8518518518518519 name: Max Recall - type: max_ap value: 0.596555546112473 name: Max Ap - task: type: binary-classification name: Binary Classification dataset: name: Qnli dev type: Qnli-dev metrics: - type: cosine_accuracy value: 0.71484375 name: Cosine Accuracy - type: cosine_accuracy_threshold value: 0.7152643799781799 name: Cosine Accuracy Threshold - type: cosine_f1 value: 0.7224334600760456 name: Cosine F1 - type: cosine_f1_threshold value: 0.6804982423782349 name: Cosine F1 Threshold - type: cosine_precision value: 0.6785714285714286 name: Cosine Precision - type: cosine_recall value: 0.7723577235772358 name: Cosine Recall - type: cosine_ap value: 0.7550328500735501 name: Cosine Ap - type: dot_accuracy value: 0.69140625 name: Dot Accuracy - type: dot_accuracy_threshold value: 720.3964233398438 name: Dot Accuracy Threshold - type: dot_f1 value: 0.7058823529411764 name: Dot F1 - type: dot_f1_threshold value: 706.561279296875 name: Dot F1 Threshold - type: dot_precision value: 0.6442953020134228 name: Dot Precision - type: dot_recall value: 0.7804878048780488 name: Dot Recall - type: dot_ap value: 0.7012253433472802 name: Dot Ap - type: manhattan_accuracy value: 0.72265625 name: Manhattan Accuracy - type: manhattan_accuracy_threshold value: 760.7179565429688 name: Manhattan Accuracy Threshold - type: manhattan_f1 value: 0.7279693486590038 name: Manhattan F1 - type: manhattan_f1_threshold value: 807.8878173828125 name: Manhattan F1 Threshold - type: manhattan_precision value: 0.6884057971014492 name: Manhattan Precision - type: manhattan_recall value: 0.7723577235772358 name: Manhattan Recall - type: manhattan_ap value: 0.7705323139232185 name: Manhattan Ap - type: euclidean_accuracy value: 0.7265625 name: Euclidean Accuracy - type: euclidean_accuracy_threshold value: 25.634429931640625 name: Euclidean Accuracy Threshold - type: euclidean_f1 value: 0.7244094488188976 name: Euclidean F1 - type: euclidean_f1_threshold value: 25.634429931640625 name: Euclidean F1 Threshold - type: euclidean_precision value: 0.7022900763358778 name: Euclidean Precision - type: euclidean_recall value: 0.7479674796747967 name: Euclidean Recall - type: euclidean_ap value: 0.7674294690555423 name: Euclidean Ap - type: max_accuracy value: 0.7265625 name: Max Accuracy - type: max_accuracy_threshold value: 760.7179565429688 name: Max Accuracy Threshold - type: max_f1 value: 0.7279693486590038 name: Max F1 - type: max_f1_threshold value: 807.8878173828125 name: Max F1 Threshold - type: max_precision value: 0.7022900763358778 name: Max Precision - type: max_recall value: 0.7804878048780488 name: Max Recall - type: max_ap value: 0.7705323139232185 name: Max Ap --- # SentenceTransformer based on BXresearch/DeBERTa2-0.9B-ST-v2 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BXresearch/DeBERTa2-0.9B-ST-v2](https://huggingface.co/BXresearch/DeBERTa2-0.9B-ST-v2) on the [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) dataset. It maps sentences & paragraphs to a 1536-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:** [BXresearch/DeBERTa2-0.9B-ST-v2](https://huggingface.co/BXresearch/DeBERTa2-0.9B-ST-v2) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 1536 tokens - **Similarity Function:** Cosine Similarity - **Training Dataset:** - [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) - **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': 1536, '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/DeBERTa2-0.9B-ST-stsb") # Run inference sentences = [ 'The boy is playing the piano.', 'The woman is pouring oil into the pan.', 'A small black and white dog is swimming in water.', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 1536] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` ## Evaluation ### Metrics #### Semantic Similarity * Dataset: `sts-test` * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.9174 | | **spearman_cosine** | **0.9293** | | pearson_manhattan | 0.9283 | | spearman_manhattan | 0.9298 | | pearson_euclidean | 0.9287 | | spearman_euclidean | 0.9302 | | pearson_dot | 0.9016 | | spearman_dot | 0.9063 | | pearson_max | 0.9287 | | spearman_max | 0.9302 | #### Binary Classification * Dataset: `allNLI-dev` * Evaluated with [BinaryClassificationEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator) | Metric | Value | |:-----------------------------|:-----------| | cosine_accuracy | 0.7539 | | cosine_accuracy_threshold | 0.7934 | | cosine_f1 | 0.6264 | | cosine_f1_threshold | 0.7288 | | cosine_precision | 0.5644 | | cosine_recall | 0.7037 | | cosine_ap | 0.5952 | | dot_accuracy | 0.7461 | | dot_accuracy_threshold | 853.77 | | dot_f1 | 0.6106 | | dot_f1_threshold | 685.5369 | | dot_precision | 0.4759 | | dot_recall | 0.8519 | | dot_ap | 0.5773 | | manhattan_accuracy | 0.7539 | | manhattan_accuracy_threshold | 654.8433 | | manhattan_f1 | 0.6244 | | manhattan_f1_threshold | 811.6582 | | manhattan_precision | 0.4929 | | manhattan_recall | 0.8519 | | manhattan_ap | 0.5966 | | euclidean_accuracy | 0.7539 | | euclidean_accuracy_threshold | 21.0488 | | euclidean_f1 | 0.6244 | | euclidean_f1_threshold | 26.1134 | | euclidean_precision | 0.4929 | | euclidean_recall | 0.8519 | | euclidean_ap | 0.595 | | max_accuracy | 0.7539 | | max_accuracy_threshold | 853.77 | | max_f1 | 0.6264 | | max_f1_threshold | 811.6582 | | max_precision | 0.5644 | | max_recall | 0.8519 | | **max_ap** | **0.5966** | #### Binary Classification * Dataset: `Qnli-dev` * Evaluated with [BinaryClassificationEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator) | Metric | Value | |:-----------------------------|:-----------| | cosine_accuracy | 0.7148 | | cosine_accuracy_threshold | 0.7153 | | cosine_f1 | 0.7224 | | cosine_f1_threshold | 0.6805 | | cosine_precision | 0.6786 | | cosine_recall | 0.7724 | | cosine_ap | 0.755 | | dot_accuracy | 0.6914 | | dot_accuracy_threshold | 720.3964 | | dot_f1 | 0.7059 | | dot_f1_threshold | 706.5613 | | dot_precision | 0.6443 | | dot_recall | 0.7805 | | dot_ap | 0.7012 | | manhattan_accuracy | 0.7227 | | manhattan_accuracy_threshold | 760.718 | | manhattan_f1 | 0.728 | | manhattan_f1_threshold | 807.8878 | | manhattan_precision | 0.6884 | | manhattan_recall | 0.7724 | | manhattan_ap | 0.7705 | | euclidean_accuracy | 0.7266 | | euclidean_accuracy_threshold | 25.6344 | | euclidean_f1 | 0.7244 | | euclidean_f1_threshold | 25.6344 | | euclidean_precision | 0.7023 | | euclidean_recall | 0.748 | | euclidean_ap | 0.7674 | | max_accuracy | 0.7266 | | max_accuracy_threshold | 760.718 | | max_f1 | 0.728 | | max_f1_threshold | 807.8878 | | max_precision | 0.7023 | | max_recall | 0.7805 | | **max_ap** | **0.7705** | ## Training Details ### Training Dataset #### sentence-transformers/stsb * Dataset: [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308) * Size: 5,749 training samples * Columns: sentence1, sentence2, and score * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | score | |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------| | type | string | string | float | | details | | | | * Samples: | sentence1 | sentence2 | score | |:-----------------------------------------------------------|:----------------------------------------------------------------------|:------------------| | A plane is taking off. | An air plane is taking off. | 1.0 | | A man is playing a large flute. | A man is playing a flute. | 0.76 | | A man is spreading shreded cheese on a pizza. | A man is spreading shredded cheese on an uncooked pizza. | 0.76 | * Loss: [AnglELoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#angleloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "pairwise_angle_sim" } ``` ### Evaluation Dataset #### sentence-transformers/stsb * Dataset: [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308) * Size: 512 evaluation samples * Columns: sentence1, sentence2, and score * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | score | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------| | type | string | string | float | | details | | | | * Samples: | sentence1 | sentence2 | score | |:--------------------------------------------------|:------------------------------------------------------|:------------------| | A man with a hard hat is dancing. | A man wearing a hard hat is dancing. | 1.0 | | A young child is riding a horse. | A child is riding a horse. | 0.95 | | A man is feeding a mouse to a snake. | The man is feeding a mouse to the snake. | 1.0 | * Loss: [AnglELoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#angleloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "pairwise_angle_sim" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_eval_batch_size`: 256 - `gradient_accumulation_steps`: 2 - `learning_rate`: 1.5e-05 - `weight_decay`: 5e-05 - `num_train_epochs`: 2 - `lr_scheduler_type`: cosine_with_min_lr - `lr_scheduler_kwargs`: {'num_cycles': 0.5, 'min_lr': 2e-06} - `warmup_ratio`: 0.2 - `save_safetensors`: False - `fp16`: True - `push_to_hub`: True - `hub_model_id`: bobox/DeBERTa2-0.9B-ST-stsb-checkpoints-tmp - `hub_strategy`: all_checkpoints - `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`: 8 - `per_device_eval_batch_size`: 256 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 2 - `eval_accumulation_steps`: None - `learning_rate`: 1.5e-05 - `weight_decay`: 5e-05 - `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_with_min_lr - `lr_scheduler_kwargs`: {'num_cycles': 0.5, 'min_lr': 2e-06} - `warmup_ratio`: 0.2 - `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/DeBERTa2-0.9B-ST-stsb-checkpoints-tmp - `hub_strategy`: all_checkpoints - `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
Click to expand | Epoch | Step | Training Loss | loss | Qnli-dev_max_ap | allNLI-dev_max_ap | sts-test_spearman_cosine | |:------:|:----:|:-------------:|:------:|:---------------:|:-----------------:|:------------------------:| | 0.0056 | 2 | 2.6549 | - | - | - | - | | 0.0111 | 4 | 2.7355 | - | - | - | - | | 0.0167 | 6 | 3.6211 | - | - | - | - | | 0.0223 | 8 | 3.0686 | - | - | - | - | | 0.0278 | 10 | 3.4113 | - | - | - | - | | 0.0334 | 12 | 2.4857 | - | - | - | - | | 0.0389 | 14 | 2.4288 | - | - | - | - | | 0.0445 | 16 | 2.6203 | - | - | - | - | | 0.0501 | 18 | 2.7441 | - | - | - | - | | 0.0556 | 20 | 3.4263 | - | - | - | - | | 0.0612 | 22 | 2.3565 | - | - | - | - | | 0.0668 | 24 | 2.5596 | - | - | - | - | | 0.0723 | 26 | 3.0866 | - | - | - | - | | 0.0779 | 28 | 3.223 | - | - | - | - | | 0.0834 | 30 | 2.012 | - | - | - | - | | 0.0890 | 32 | 3.2829 | - | - | - | - | | 0.0946 | 34 | 3.9277 | - | - | - | - | | 0.1001 | 36 | 2.785 | 2.6652 | 0.7960 | 0.6275 | 0.9294 | | 0.1057 | 38 | 3.4966 | - | - | - | - | | 0.1113 | 40 | 2.5923 | - | - | - | - | | 0.1168 | 42 | 3.4418 | - | - | - | - | | 0.1224 | 44 | 2.6519 | - | - | - | - | | 0.1280 | 46 | 3.7746 | - | - | - | - | | 0.1335 | 48 | 2.6736 | - | - | - | - | | 0.1391 | 50 | 3.6764 | - | - | - | - | | 0.1446 | 52 | 3.5311 | - | - | - | - | | 0.1502 | 54 | 2.5869 | - | - | - | - | | 0.1558 | 56 | 3.183 | - | - | - | - | | 0.1613 | 58 | 2.747 | - | - | - | - | | 0.1669 | 60 | 1.965 | - | - | - | - | | 0.1725 | 62 | 2.1785 | - | - | - | - | | 0.1780 | 64 | 2.5788 | - | - | - | - | | 0.1836 | 66 | 3.1776 | - | - | - | - | | 0.1892 | 68 | 2.6464 | - | - | - | - | | 0.1947 | 70 | 2.7619 | - | - | - | - | | 0.2003 | 72 | 3.0911 | 2.6171 | 0.7923 | 0.6295 | 0.9276 | | 0.2058 | 74 | 2.4308 | - | - | - | - | | 0.2114 | 76 | 3.2068 | - | - | - | - | | 0.2170 | 78 | 2.4081 | - | - | - | - | | 0.2225 | 80 | 2.3257 | - | - | - | - | | 0.2281 | 82 | 3.0499 | - | - | - | - | | 0.2337 | 84 | 3.2518 | - | - | - | - | | 0.2392 | 86 | 2.7876 | - | - | - | - | | 0.2448 | 88 | 2.7898 | - | - | - | - | | 0.2503 | 90 | 2.7116 | - | - | - | - | | 0.2559 | 92 | 3.0505 | - | - | - | - | | 0.2615 | 94 | 2.5901 | - | - | - | - | | 0.2670 | 96 | 1.9563 | - | - | - | - | | 0.2726 | 98 | 2.1006 | - | - | - | - | | 0.2782 | 100 | 2.1853 | - | - | - | - | | 0.2837 | 102 | 2.327 | - | - | - | - | | 0.2893 | 104 | 1.9937 | - | - | - | - | | 0.2949 | 106 | 2.543 | - | - | - | - | | 0.3004 | 108 | 1.9826 | 2.4596 | 0.7919 | 0.6329 | 0.9341 | | 0.3060 | 110 | 3.0746 | - | - | - | - | | 0.3115 | 112 | 2.4145 | - | - | - | - | | 0.3171 | 114 | 2.244 | - | - | - | - | | 0.3227 | 116 | 2.78 | - | - | - | - | | 0.3282 | 118 | 2.8323 | - | - | - | - | | 0.3338 | 120 | 2.4639 | - | - | - | - | | 0.3394 | 122 | 2.9216 | - | - | - | - | | 0.3449 | 124 | 2.0747 | - | - | - | - | | 0.3505 | 126 | 2.7573 | - | - | - | - | | 0.3561 | 128 | 3.7019 | - | - | - | - | | 0.3616 | 130 | 3.3155 | - | - | - | - | | 0.3672 | 132 | 3.625 | - | - | - | - | | 0.3727 | 134 | 3.2889 | - | - | - | - | | 0.3783 | 136 | 3.5936 | - | - | - | - | | 0.3839 | 138 | 3.5932 | - | - | - | - | | 0.3894 | 140 | 3.0457 | - | - | - | - | | 0.3950 | 142 | 3.093 | - | - | - | - | | 0.4006 | 144 | 2.7189 | 2.4698 | 0.7752 | 0.5896 | 0.9346 | | 0.4061 | 146 | 3.2578 | - | - | - | - | | 0.4117 | 148 | 3.3581 | - | - | - | - | | 0.4172 | 150 | 2.9734 | - | - | - | - | | 0.4228 | 152 | 3.0514 | - | - | - | - | | 0.4284 | 154 | 3.1983 | - | - | - | - | | 0.4339 | 156 | 2.9033 | - | - | - | - | | 0.4395 | 158 | 2.9279 | - | - | - | - | | 0.4451 | 160 | 3.1336 | - | - | - | - | | 0.4506 | 162 | 3.1467 | - | - | - | - | | 0.4562 | 164 | 3.0381 | - | - | - | - | | 0.4618 | 166 | 3.068 | - | - | - | - | | 0.4673 | 168 | 3.0261 | - | - | - | - | | 0.4729 | 170 | 3.2867 | - | - | - | - | | 0.4784 | 172 | 2.8474 | - | - | - | - | | 0.4840 | 174 | 2.7982 | - | - | - | - | | 0.4896 | 176 | 2.7945 | - | - | - | - | | 0.4951 | 178 | 3.1312 | - | - | - | - | | 0.5007 | 180 | 2.9704 | 2.4640 | 0.7524 | 0.6033 | 0.9242 | | 0.5063 | 182 | 2.9856 | - | - | - | - | | 0.5118 | 184 | 3.014 | - | - | - | - | | 0.5174 | 186 | 3.0125 | - | - | - | - | | 0.5229 | 188 | 2.8149 | - | - | - | - | | 0.5285 | 190 | 2.7954 | - | - | - | - | | 0.5341 | 192 | 3.078 | - | - | - | - | | 0.5396 | 194 | 2.955 | - | - | - | - | | 0.5452 | 196 | 2.9468 | - | - | - | - | | 0.5508 | 198 | 3.0791 | - | - | - | - | | 0.5563 | 200 | 2.998 | - | - | - | - | | 0.5619 | 202 | 2.9068 | - | - | - | - | | 0.5675 | 204 | 2.8283 | - | - | - | - | | 0.5730 | 206 | 2.9216 | - | - | - | - | | 0.5786 | 208 | 3.3441 | - | - | - | - | | 0.5841 | 210 | 3.0 | - | - | - | - | | 0.5897 | 212 | 2.9023 | - | - | - | - | | 0.5953 | 214 | 2.8177 | - | - | - | - | | 0.6008 | 216 | 2.8262 | 2.4979 | 0.7899 | 0.6037 | 0.9260 | | 0.6064 | 218 | 2.7832 | - | - | - | - | | 0.6120 | 220 | 3.0085 | - | - | - | - | | 0.6175 | 222 | 2.8762 | - | - | - | - | | 0.6231 | 224 | 3.147 | - | - | - | - | | 0.6287 | 226 | 3.4262 | - | - | - | - | | 0.6342 | 228 | 2.8271 | - | - | - | - | | 0.6398 | 230 | 2.4024 | - | - | - | - | | 0.6453 | 232 | 2.7556 | - | - | - | - | | 0.6509 | 234 | 3.4652 | - | - | - | - | | 0.6565 | 236 | 2.7235 | - | - | - | - | | 0.6620 | 238 | 2.6498 | - | - | - | - | | 0.6676 | 240 | 3.0933 | - | - | - | - | | 0.6732 | 242 | 3.1193 | - | - | - | - | | 0.6787 | 244 | 2.7249 | - | - | - | - | | 0.6843 | 246 | 2.8931 | - | - | - | - | | 0.6898 | 248 | 2.7913 | - | - | - | - | | 0.6954 | 250 | 2.6933 | - | - | - | - | | 0.7010 | 252 | 2.5632 | 2.4585 | 0.7700 | 0.6065 | 0.9298 | | 0.7065 | 254 | 2.8347 | - | - | - | - | | 0.7121 | 256 | 2.3827 | - | - | - | - | | 0.7177 | 258 | 2.9065 | - | - | - | - | | 0.7232 | 260 | 2.8162 | - | - | - | - | | 0.7288 | 262 | 2.5485 | - | - | - | - | | 0.7344 | 264 | 2.5751 | - | - | - | - | | 0.7399 | 266 | 2.9056 | - | - | - | - | | 0.7455 | 268 | 3.1397 | - | - | - | - | | 0.7510 | 270 | 3.3107 | - | - | - | - | | 0.7566 | 272 | 2.9024 | - | - | - | - | | 0.7622 | 274 | 2.2307 | - | - | - | - | | 0.7677 | 276 | 3.0097 | - | - | - | - | | 0.7733 | 278 | 3.1406 | - | - | - | - | | 0.7789 | 280 | 2.6786 | - | - | - | - | | 0.7844 | 282 | 2.8882 | - | - | - | - | | 0.7900 | 284 | 2.7215 | - | - | - | - | | 0.7955 | 286 | 3.4188 | - | - | - | - | | 0.8011 | 288 | 2.9901 | 2.4414 | 0.7665 | 0.6023 | 0.9288 | | 0.8067 | 290 | 2.5144 | - | - | - | - | | 0.8122 | 292 | 3.1932 | - | - | - | - | | 0.8178 | 294 | 2.9733 | - | - | - | - | | 0.8234 | 296 | 2.6895 | - | - | - | - | | 0.8289 | 298 | 2.678 | - | - | - | - | | 0.8345 | 300 | 2.5462 | - | - | - | - | | 0.8401 | 302 | 2.6911 | - | - | - | - | | 0.8456 | 304 | 2.8404 | - | - | - | - | | 0.8512 | 306 | 2.5358 | - | - | - | - | | 0.8567 | 308 | 3.1245 | - | - | - | - | | 0.8623 | 310 | 2.3404 | - | - | - | - | | 0.8679 | 312 | 3.0751 | - | - | - | - | | 0.8734 | 314 | 2.7005 | - | - | - | - | | 0.8790 | 316 | 2.7387 | - | - | - | - | | 0.8846 | 318 | 2.7227 | - | - | - | - | | 0.8901 | 320 | 2.9085 | - | - | - | - | | 0.8957 | 322 | 3.3239 | - | - | - | - | | 0.9013 | 324 | 2.4256 | 2.4106 | 0.7644 | 0.6087 | 0.9304 | | 0.9068 | 326 | 2.5059 | - | - | - | - | | 0.9124 | 328 | 2.5387 | - | - | - | - | | 0.9179 | 330 | 2.899 | - | - | - | - | | 0.9235 | 332 | 2.7256 | - | - | - | - | | 0.9291 | 334 | 2.4862 | - | - | - | - | | 0.9346 | 336 | 3.0014 | - | - | - | - | | 0.9402 | 338 | 2.4164 | - | - | - | - | | 0.9458 | 340 | 2.3148 | - | - | - | - | | 0.9513 | 342 | 2.9414 | - | - | - | - | | 0.9569 | 344 | 2.4435 | - | - | - | - | | 0.9624 | 346 | 2.6286 | - | - | - | - | | 0.9680 | 348 | 2.1744 | - | - | - | - | | 0.9736 | 350 | 2.5866 | - | - | - | - | | 0.9791 | 352 | 2.8333 | - | - | - | - | | 0.9847 | 354 | 2.3544 | - | - | - | - | | 0.9903 | 356 | 2.5397 | - | - | - | - | | 0.9958 | 358 | 3.4058 | - | - | - | - | | 1.0014 | 360 | 2.2904 | 2.4089 | 0.7888 | 0.6104 | 0.9338 | | 1.0070 | 362 | 2.7925 | - | - | - | - | | 1.0125 | 364 | 2.6415 | - | - | - | - | | 1.0181 | 366 | 2.724 | - | - | - | - | | 1.0236 | 368 | 2.569 | - | - | - | - | | 1.0292 | 370 | 2.808 | - | - | - | - | | 1.0348 | 372 | 2.4672 | - | - | - | - | | 1.0403 | 374 | 2.3964 | - | - | - | - | | 1.0459 | 376 | 2.3518 | - | - | - | - | | 1.0515 | 378 | 2.7617 | - | - | - | - | | 1.0570 | 380 | 2.5651 | - | - | - | - | | 1.0626 | 382 | 2.2623 | - | - | - | - | | 1.0682 | 384 | 2.2048 | - | - | - | - | | 1.0737 | 386 | 2.1426 | - | - | - | - | | 1.0793 | 388 | 1.8182 | - | - | - | - | | 1.0848 | 390 | 2.3166 | - | - | - | - | | 1.0904 | 392 | 2.4101 | - | - | - | - | | 1.0960 | 394 | 2.8932 | - | - | - | - | | 1.1015 | 396 | 3.0201 | 2.4217 | 0.7851 | 0.6205 | 0.9301 | | 1.1071 | 398 | 2.6101 | - | - | - | - | | 1.1127 | 400 | 2.3627 | - | - | - | - | | 1.1182 | 402 | 2.5402 | - | - | - | - | | 1.1238 | 404 | 2.695 | - | - | - | - | | 1.1293 | 406 | 3.0563 | - | - | - | - | | 1.1349 | 408 | 2.2296 | - | - | - | - | | 1.1405 | 410 | 3.057 | - | - | - | - | | 1.1460 | 412 | 2.8023 | - | - | - | - | | 1.1516 | 414 | 2.6492 | - | - | - | - | | 1.1572 | 416 | 2.2406 | - | - | - | - | | 1.1627 | 418 | 1.7195 | - | - | - | - | | 1.1683 | 420 | 2.2773 | - | - | - | - | | 1.1739 | 422 | 2.3639 | - | - | - | - | | 1.1794 | 424 | 2.3348 | - | - | - | - | | 1.1850 | 426 | 2.6791 | - | - | - | - | | 1.1905 | 428 | 2.3621 | - | - | - | - | | 1.1961 | 430 | 2.5224 | - | - | - | - | | 1.2017 | 432 | 2.4063 | 2.4724 | 0.7628 | 0.6043 | 0.9270 | | 1.2072 | 434 | 1.9713 | - | - | - | - | | 1.2128 | 436 | 2.4265 | - | - | - | - | | 1.2184 | 438 | 2.0827 | - | - | - | - | | 1.2239 | 440 | 2.0696 | - | - | - | - | | 1.2295 | 442 | 2.7507 | - | - | - | - | | 1.2350 | 444 | 2.5436 | - | - | - | - | | 1.2406 | 446 | 2.4039 | - | - | - | - | | 1.2462 | 448 | 2.4229 | - | - | - | - | | 1.2517 | 450 | 2.323 | - | - | - | - | | 1.2573 | 452 | 2.6099 | - | - | - | - | | 1.2629 | 454 | 2.0329 | - | - | - | - | | 1.2684 | 456 | 1.8797 | - | - | - | - | | 1.2740 | 458 | 1.4485 | - | - | - | - | | 1.2796 | 460 | 1.6794 | - | - | - | - | | 1.2851 | 462 | 2.0934 | - | - | - | - | | 1.2907 | 464 | 1.9579 | - | - | - | - | | 1.2962 | 466 | 1.9288 | - | - | - | - | | 1.3018 | 468 | 1.5874 | 2.5056 | 0.7833 | 0.5948 | 0.9345 | | 1.3074 | 470 | 1.8715 | - | - | - | - | | 1.3129 | 472 | 1.3778 | - | - | - | - | | 1.3185 | 474 | 2.2242 | - | - | - | - | | 1.3241 | 476 | 2.4031 | - | - | - | - | | 1.3296 | 478 | 1.924 | - | - | - | - | | 1.3352 | 480 | 1.7895 | - | - | - | - | | 1.3408 | 482 | 2.0349 | - | - | - | - | | 1.3463 | 484 | 1.8116 | - | - | - | - | | 1.3519 | 486 | 2.353 | - | - | - | - | | 1.3574 | 488 | 3.4263 | - | - | - | - | | 1.3630 | 490 | 4.0606 | - | - | - | - | | 1.3686 | 492 | 2.7423 | - | - | - | - | | 1.3741 | 494 | 2.8461 | - | - | - | - | | 1.3797 | 496 | 3.0742 | - | - | - | - | | 1.3853 | 498 | 2.2054 | - | - | - | - | | 1.3908 | 500 | 2.6009 | - | - | - | - | | 1.3964 | 502 | 2.242 | - | - | - | - | | 1.4019 | 504 | 2.9416 | 2.5288 | 0.7969 | 0.6010 | 0.9323 | | 1.4075 | 506 | 3.8179 | - | - | - | - | | 1.4131 | 508 | 3.0147 | - | - | - | - | | 1.4186 | 510 | 2.2185 | - | - | - | - | | 1.4242 | 512 | 3.0323 | - | - | - | - | | 1.4298 | 514 | 2.6922 | - | - | - | - | | 1.4353 | 516 | 2.6219 | - | - | - | - | | 1.4409 | 518 | 2.4365 | - | - | - | - | | 1.4465 | 520 | 3.1643 | - | - | - | - | | 1.4520 | 522 | 2.5548 | - | - | - | - | | 1.4576 | 524 | 2.3798 | - | - | - | - | | 1.4631 | 526 | 2.6361 | - | - | - | - | | 1.4687 | 528 | 2.6859 | - | - | - | - | | 1.4743 | 530 | 2.6071 | - | - | - | - | | 1.4798 | 532 | 2.2565 | - | - | - | - | | 1.4854 | 534 | 2.2415 | - | - | - | - | | 1.4910 | 536 | 2.4591 | - | - | - | - | | 1.4965 | 538 | 2.6729 | - | - | - | - | | 1.5021 | 540 | 2.3898 | 2.5025 | 0.7881 | 0.5978 | 0.9300 | | 1.5076 | 542 | 2.4614 | - | - | - | - | | 1.5132 | 544 | 2.5447 | - | - | - | - | | 1.5188 | 546 | 2.502 | - | - | - | - | | 1.5243 | 548 | 2.1892 | - | - | - | - | | 1.5299 | 550 | 2.7081 | - | - | - | - | | 1.5355 | 552 | 2.5523 | - | - | - | - | | 1.5410 | 554 | 2.3571 | - | - | - | - | | 1.5466 | 556 | 2.7694 | - | - | - | - | | 1.5522 | 558 | 2.2 | - | - | - | - | | 1.5577 | 560 | 2.4179 | - | - | - | - | | 1.5633 | 562 | 2.3914 | - | - | - | - | | 1.5688 | 564 | 2.1722 | - | - | - | - | | 1.5744 | 566 | 2.345 | - | - | - | - | | 1.5800 | 568 | 3.0069 | - | - | - | - | | 1.5855 | 570 | 2.4231 | - | - | - | - | | 1.5911 | 572 | 2.3597 | - | - | - | - | | 1.5967 | 574 | 2.143 | - | - | - | - | | 1.6022 | 576 | 2.6288 | 2.5368 | 0.7943 | 0.6048 | 0.9265 | | 1.6078 | 578 | 2.3905 | - | - | - | - | | 1.6134 | 580 | 2.1823 | - | - | - | - | | 1.6189 | 582 | 2.367 | - | - | - | - | | 1.6245 | 584 | 2.8189 | - | - | - | - | | 1.6300 | 586 | 2.6536 | - | - | - | - | | 1.6356 | 588 | 2.2134 | - | - | - | - | | 1.6412 | 590 | 1.6949 | - | - | - | - | | 1.6467 | 592 | 2.2029 | - | - | - | - | | 1.6523 | 594 | 3.0223 | - | - | - | - | | 1.6579 | 596 | 2.239 | - | - | - | - | | 1.6634 | 598 | 2.3388 | - | - | - | - | | 1.6690 | 600 | 2.3066 | - | - | - | - | | 1.6745 | 602 | 2.4762 | - | - | - | - | | 1.6801 | 604 | 1.9503 | - | - | - | - | | 1.6857 | 606 | 2.1252 | - | - | - | - | | 1.6912 | 608 | 1.8253 | - | - | - | - | | 1.6968 | 610 | 2.2938 | - | - | - | - | | 1.7024 | 612 | 1.9489 | 2.5747 | 0.7675 | 0.5964 | 0.9267 | | 1.7079 | 614 | 1.9238 | - | - | - | - | | 1.7135 | 616 | 1.8171 | - | - | - | - | | 1.7191 | 618 | 2.2371 | - | - | - | - | | 1.7246 | 620 | 2.4901 | - | - | - | - | | 1.7302 | 622 | 1.8503 | - | - | - | - | | 1.7357 | 624 | 2.017 | - | - | - | - | | 1.7413 | 626 | 2.3069 | - | - | - | - | | 1.7469 | 628 | 2.444 | - | - | - | - | | 1.7524 | 630 | 1.9606 | - | - | - | - | | 1.7580 | 632 | 2.2364 | - | - | - | - | | 1.7636 | 634 | 1.8711 | - | - | - | - | | 1.7691 | 636 | 2.4233 | - | - | - | - | | 1.7747 | 638 | 2.4065 | - | - | - | - | | 1.7803 | 640 | 2.0725 | - | - | - | - | | 1.7858 | 642 | 2.0578 | - | - | - | - | | 1.7914 | 644 | 2.2066 | - | - | - | - | | 1.7969 | 646 | 1.7767 | - | - | - | - | | 1.8025 | 648 | 2.7388 | 2.5685 | 0.7663 | 0.5959 | 0.9292 | | 1.8081 | 650 | 1.854 | - | - | - | - | | 1.8136 | 652 | 2.7337 | - | - | - | - | | 1.8192 | 654 | 2.4477 | - | - | - | - | | 1.8248 | 656 | 2.4818 | - | - | - | - | | 1.8303 | 658 | 1.8592 | - | - | - | - | | 1.8359 | 660 | 1.8396 | - | - | - | - | | 1.8414 | 662 | 2.3893 | - | - | - | - | | 1.8470 | 664 | 2.0139 | - | - | - | - | | 1.8526 | 666 | 2.8837 | - | - | - | - | | 1.8581 | 668 | 2.0342 | - | - | - | - | | 1.8637 | 670 | 1.8857 | - | - | - | - | | 1.8693 | 672 | 2.1147 | - | - | - | - | | 1.8748 | 674 | 1.6263 | - | - | - | - | | 1.8804 | 676 | 2.2987 | - | - | - | - | | 1.8860 | 678 | 1.9678 | - | - | - | - | | 1.8915 | 680 | 1.9999 | - | - | - | - | | 1.8971 | 682 | 2.2802 | - | - | - | - | | 1.9026 | 684 | 1.9666 | 2.5536 | 0.7717 | 0.5967 | 0.9289 | | 1.9082 | 686 | 1.8156 | - | - | - | - | | 1.9138 | 688 | 1.9542 | - | - | - | - | | 1.9193 | 690 | 1.859 | - | - | - | - | | 1.9249 | 692 | 1.6237 | - | - | - | - | | 1.9305 | 694 | 2.3085 | - | - | - | - | | 1.9360 | 696 | 2.1461 | - | - | - | - | | 1.9416 | 698 | 1.7024 | - | - | - | - | | 1.9471 | 700 | 2.2181 | - | - | - | - | | 1.9527 | 702 | 2.4782 | - | - | - | - | | 1.9583 | 704 | 1.7378 | - | - | - | - | | 1.9638 | 706 | 2.0422 | - | - | - | - | | 1.9694 | 708 | 1.7577 | - | - | - | - | | 1.9750 | 710 | 2.0209 | - | - | - | - | | 1.9805 | 712 | 2.0372 | - | - | - | - | | 1.9861 | 714 | 2.0915 | - | - | - | - | | 1.9917 | 716 | 1.603 | - | - | - | - | | 1.9972 | 718 | 1.7111 | 2.5566 | 0.7705 | 0.5966 | 0.9293 |
### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.0.1 - Transformers: 4.42.4 - PyTorch: 2.4.0+cu121 - Accelerate: 0.32.1 - Datasets: 2.21.0 - 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", } ``` #### AnglELoss ```bibtex @misc{li2023angleoptimized, title={AnglE-optimized Text Embeddings}, author={Xianming Li and Jing Li}, year={2023}, eprint={2309.12871}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```