--- language: - en tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:100000 - loss:OnlineContrastiveLoss base_model: sentence-transformers/stsb-distilbert-base widget: - source_sentence: Can I retrieve my deleted text messages on my LG phone? sentences: - Why do we sleep? - How do I recover a deleted text message from my phone without a computer? - What are subjects to study in upsc? - source_sentence: How can I prepare for IPS? sentences: - What should I prepare for ips? - I am trying to find a meaning to life, to give a purpose to my life. Is there any book that can help me find my answer, or at least give me the tools? - What are the health benefits of Turmeric? - source_sentence: Which is the best game development laptop for ₹60,000 to ₹70,000 INR? sentences: - Why doesn't Palestine appear on Google Maps as of 2016? - Which is the best laptop for game development under ₹70,000 INR? - What is meant by judicial review in the context of the Indian Judiciary? - source_sentence: Although light beam bouncing between two plates inside a clock is often used to explain time dilation, how can other practical cases be explained? sentences: - Is Run Ze Cao's falsification of Einstein's relativity valid? - If India denies Pakistan water, will Pakistan give up its nuclear weapons? - How do I revise class 12 syllabus in 1 month? - source_sentence: How can I lose weight quickly? Need serious help. sentences: - Which is the best romantic movie? - Why are there so many half-built, abandoned buildings in Mexico? - How can you lose weight really quick? datasets: - sentence-transformers/quora-duplicates pipeline_tag: sentence-similarity library_name: sentence-transformers metrics: - cosine_accuracy - cosine_accuracy_threshold - cosine_f1 - cosine_f1_threshold - cosine_precision - cosine_recall - cosine_ap - cosine_mcc - average_precision - f1 - precision - recall - threshold - cosine_accuracy@1 - cosine_accuracy@3 - cosine_accuracy@5 - cosine_accuracy@10 - cosine_precision@1 - cosine_precision@3 - cosine_precision@5 - cosine_precision@10 - cosine_recall@1 - cosine_recall@3 - cosine_recall@5 - cosine_recall@10 - cosine_ndcg@10 - cosine_mrr@10 - cosine_map@100 model-index: - name: SentenceTransformer based on sentence-transformers/stsb-distilbert-base results: - task: type: binary-classification name: Binary Classification dataset: name: quora duplicates type: quora-duplicates metrics: - type: cosine_accuracy value: 0.866 name: Cosine Accuracy - type: cosine_accuracy_threshold value: 0.7860240340232849 name: Cosine Accuracy Threshold - type: cosine_f1 value: 0.8320802005012532 name: Cosine F1 - type: cosine_f1_threshold value: 0.7848798036575317 name: Cosine F1 Threshold - type: cosine_precision value: 0.7811764705882352 name: Cosine Precision - type: cosine_recall value: 0.8900804289544236 name: Cosine Recall - type: cosine_ap value: 0.8772887253419398 name: Cosine Ap - type: cosine_mcc value: 0.7256385093029618 name: Cosine Mcc - task: type: paraphrase-mining name: Paraphrase Mining dataset: name: quora duplicates dev type: quora-duplicates-dev metrics: - type: average_precision value: 0.6392503009812087 name: Average Precision - type: f1 value: 0.6435291762586327 name: F1 - type: precision value: 0.644658344613225 name: Precision - type: recall value: 0.6424039566368587 name: Recall - type: threshold value: 0.8726956844329834 name: Threshold - task: type: information-retrieval name: Information Retrieval dataset: name: Unknown type: unknown metrics: - type: cosine_accuracy@1 value: 0.9172 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.9588 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.9672 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.9762 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.9172 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.4102 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.2644 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.14058 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.7868590910037675 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.91981069059372 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.9442488336402158 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.9641439212486859 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.9388257874901692 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.9393049206349205 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.9258332306777016 name: Cosine Map@100 --- # SentenceTransformer based on sentence-transformers/stsb-distilbert-base This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/stsb-distilbert-base](https://huggingface.co/sentence-transformers/stsb-distilbert-base) on the [quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) 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:** [sentence-transformers/stsb-distilbert-base](https://huggingface.co/sentence-transformers/stsb-distilbert-base) - **Maximum Sequence Length:** 128 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity - **Training Dataset:** - [quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) - **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': 128, '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("CalebR84/stsb-distilbert-base-ocl") # Run inference sentences = [ 'How can I lose weight quickly? Need serious help.', 'How can you lose weight really quick?', 'Why are there so many half-built, abandoned buildings in Mexico?', ] 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 * Dataset: `quora-duplicates` * Evaluated with [BinaryClassificationEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator) | Metric | Value | |:--------------------------|:-----------| | cosine_accuracy | 0.866 | | cosine_accuracy_threshold | 0.786 | | cosine_f1 | 0.8321 | | cosine_f1_threshold | 0.7849 | | cosine_precision | 0.7812 | | cosine_recall | 0.8901 | | **cosine_ap** | **0.8773** | | cosine_mcc | 0.7256 | #### Paraphrase Mining * Dataset: `quora-duplicates-dev` * Evaluated with [ParaphraseMiningEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.ParaphraseMiningEvaluator) with these parameters: ```json {'add_transitive_closure': , 'max_pairs': 500000, 'top_k': 100} ``` | Metric | Value | |:----------------------|:-----------| | **average_precision** | **0.6393** | | f1 | 0.6435 | | precision | 0.6447 | | recall | 0.6424 | | threshold | 0.8727 | #### Information Retrieval * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.9172 | | cosine_accuracy@3 | 0.9588 | | cosine_accuracy@5 | 0.9672 | | cosine_accuracy@10 | 0.9762 | | cosine_precision@1 | 0.9172 | | cosine_precision@3 | 0.4102 | | cosine_precision@5 | 0.2644 | | cosine_precision@10 | 0.1406 | | cosine_recall@1 | 0.7869 | | cosine_recall@3 | 0.9198 | | cosine_recall@5 | 0.9442 | | cosine_recall@10 | 0.9641 | | **cosine_ndcg@10** | **0.9388** | | cosine_mrr@10 | 0.9393 | | cosine_map@100 | 0.9258 | ## Training Details ### Training Dataset #### quora-duplicates * Dataset: [quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb) * Size: 100,000 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 | |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------|:---------------| | What are some of the greatest books not adapted into film yet? | What book should be made into a movie? | 0 | | How can I increase my communication skills? | How we improve our communication skills? | 1 | | Heymen I have a note5 it give me this message when a turn it on and shout down (custom pinary are blocked by frp lock) I try odin and kies butnot work? | Setup dubbing studio with very less budget in India? | 0 | * Loss: [OnlineContrastiveLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss) ### Evaluation Dataset #### quora-duplicates * Dataset: [quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb) * Size: 1,000 evaluation 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 | |:------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------|:---------------| | Which is the best book to learn data structures and algorithms? | Which book is the best book for algorithm and datastructure? | 1 | | Does modafinil shows up on a drug test? Because my urine smells a lot of medicine? | Can Modafinil come out in a drug test? | 0 | | Does the size of a penis matter? | Does penis size matters for girls? | 1 | * Loss: [OnlineContrastiveLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss) ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 64 - `per_device_eval_batch_size`: 64 - `num_train_epochs`: 10 - `warmup_ratio`: 0.1 - `fp16`: 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 - `torch_empty_cache_steps`: None - `learning_rate`: 5e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 10 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.1 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: True - `save_on_each_node`: False - `save_only_model`: False - `restore_callback_states_from_checkpoint`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `use_ipex`: False - `bf16`: False - `fp16`: True - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `local_rank`: 0 - `ddp_backend`: None - `tpu_num_cores`: None - `tpu_metrics_debug`: False - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: False - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `tp_size`: 0 - `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`: None - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `include_for_metrics`: [] - `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 - `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 - `use_liger_kernel`: False - `eval_use_gather_object`: False - `average_tokens_across_devices`: False - `prompts`: None - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional
### Training Logs
Click to expand | Epoch | Step | Training Loss | Validation Loss | quora-duplicates_cosine_ap | quora-duplicates-dev_average_precision | cosine_ndcg@10 | |:------:|:-----:|:-------------:|:---------------:|:--------------------------:|:--------------------------------------:|:--------------:| | 0 | 0 | - | - | 0.6905 | 0.4200 | 0.9397 | | 0.0640 | 100 | 2.6402 | - | - | - | - | | 0.1280 | 200 | 2.4398 | - | - | - | - | | 0.1599 | 250 | - | 2.4217 | 0.7392 | 0.4765 | 0.9426 | | 0.1919 | 300 | 2.2461 | - | - | - | - | | 0.2559 | 400 | 2.1433 | - | - | - | - | | 0.3199 | 500 | 2.0417 | 2.1120 | 0.7970 | 0.4566 | 0.9429 | | 0.3839 | 600 | 2.0441 | - | - | - | - | | 0.4479 | 700 | 1.8907 | - | - | - | - | | 0.4798 | 750 | - | 2.0011 | 0.8229 | 0.4820 | 0.9468 | | 0.5118 | 800 | 1.8985 | - | - | - | - | | 0.5758 | 900 | 1.7521 | - | - | - | - | | 0.6398 | 1000 | 1.8888 | 1.8010 | 0.8382 | 0.4925 | 0.9425 | | 0.7038 | 1100 | 1.8524 | - | - | - | - | | 0.7678 | 1200 | 1.6956 | - | - | - | - | | 0.7997 | 1250 | - | 1.8004 | 0.8438 | 0.4283 | 0.9336 | | 0.8317 | 1300 | 1.7519 | - | - | - | - | | 0.8957 | 1400 | 1.7515 | - | - | - | - | | 0.9597 | 1500 | 1.7288 | 1.7434 | 0.8352 | 0.5050 | 0.9428 | | 1.0237 | 1600 | 1.533 | - | - | - | - | | 1.0877 | 1700 | 1.2543 | - | - | - | - | | 1.1196 | 1750 | - | 1.7109 | 0.8514 | 0.5299 | 0.9415 | | 1.1516 | 1800 | 1.3201 | - | - | - | - | | 1.2156 | 1900 | 1.3309 | - | - | - | - | | 1.2796 | 2000 | 1.3256 | 1.7111 | 0.8528 | 0.5138 | 0.9393 | | 1.3436 | 2100 | 1.2865 | - | - | - | - | | 1.4075 | 2200 | 1.2659 | - | - | - | - | | 1.4395 | 2250 | - | 1.7974 | 0.8468 | 0.5320 | 0.9390 | | 1.4715 | 2300 | 1.2601 | - | - | - | - | | 1.5355 | 2400 | 1.3337 | - | - | - | - | | 1.5995 | 2500 | 1.3319 | 1.6922 | 0.8575 | 0.5399 | 0.9416 | | 1.6635 | 2600 | 1.3232 | - | - | - | - | | 1.7274 | 2700 | 1.3684 | - | - | - | - | | 1.7594 | 2750 | - | 1.5772 | 0.8581 | 0.5592 | 0.9484 | | 1.7914 | 2800 | 1.2706 | - | - | - | - | | 1.8554 | 2900 | 1.3186 | - | - | - | - | | 1.9194 | 3000 | 1.2336 | 1.5423 | 0.8656 | 0.5749 | 0.9433 | | 1.9834 | 3100 | 1.2193 | - | - | - | - | | 2.0473 | 3200 | 0.868 | - | - | - | - | | 2.0793 | 3250 | - | 1.6575 | 0.8632 | 0.5735 | 0.9395 | | 2.1113 | 3300 | 0.6411 | - | - | - | - | | 2.1753 | 3400 | 0.7127 | - | - | - | - | | 2.2393 | 3500 | 0.7044 | 1.5778 | 0.8718 | 0.5823 | 0.9387 | | 2.3033 | 3600 | 0.6299 | - | - | - | - | | 2.3672 | 3700 | 0.7162 | - | - | - | - | | 2.3992 | 3750 | - | 1.6300 | 0.8595 | 0.5936 | 0.9414 | | 2.4312 | 3800 | 0.6642 | - | - | - | - | | 2.4952 | 3900 | 0.6902 | - | - | - | - | | 2.5592 | 4000 | 0.7959 | 1.6070 | 0.8637 | 0.6006 | 0.9363 | | 2.6232 | 4100 | 0.7588 | - | - | - | - | | 2.6871 | 4200 | 0.6925 | - | - | - | - | | 2.7191 | 4250 | - | 1.6787 | 0.8682 | 0.6006 | 0.9411 | | 2.7511 | 4300 | 0.7226 | - | - | - | - | | 2.8151 | 4400 | 0.7507 | - | - | - | - | | 2.8791 | 4500 | 0.7563 | 1.6040 | 0.8658 | 0.6061 | 0.9416 | | 2.9431 | 4600 | 0.7737 | - | - | - | - | | 3.0070 | 4700 | 0.6525 | - | - | - | - | | 3.0390 | 4750 | - | 1.6782 | 0.8652 | 0.5983 | 0.9401 | | 3.0710 | 4800 | 0.3831 | - | - | - | - | | 3.1350 | 4900 | 0.297 | - | - | - | - | | 3.1990 | 5000 | 0.3725 | 1.7229 | 0.8588 | 0.6175 | 0.9418 | | 3.2630 | 5100 | 0.4142 | - | - | - | - | | 3.3269 | 5200 | 0.4415 | - | - | - | - | | 3.3589 | 5250 | - | 1.6564 | 0.8635 | 0.6026 | 0.9379 | | 3.3909 | 5300 | 0.3729 | - | - | - | - | | 3.4549 | 5400 | 0.4164 | - | - | - | - | | 3.5189 | 5500 | 0.3668 | 1.5964 | 0.8677 | 0.6105 | 0.9358 | | 3.5829 | 5600 | 0.4184 | - | - | - | - | | 3.6468 | 5700 | 0.4311 | - | - | - | - | | 3.6788 | 5750 | - | 1.6523 | 0.8680 | 0.6130 | 0.9365 | | 3.7108 | 5800 | 0.4222 | - | - | - | - | | 3.7748 | 5900 | 0.4302 | - | - | - | - | | 3.8388 | 6000 | 0.428 | 1.6625 | 0.8674 | 0.6163 | 0.9370 | | 3.9028 | 6100 | 0.3898 | - | - | - | - | | 3.9667 | 6200 | 0.4255 | - | - | - | - | | 3.9987 | 6250 | - | 1.6145 | 0.8680 | 0.6118 | 0.9347 | | 4.0307 | 6300 | 0.3456 | - | - | - | - | | 4.0947 | 6400 | 0.2265 | - | - | - | - | | 4.1587 | 6500 | 0.1913 | 1.7208 | 0.8595 | 0.6339 | 0.9433 | | 4.2226 | 6600 | 0.2258 | - | - | - | - | | 4.2866 | 6700 | 0.2484 | - | - | - | - | | 4.3186 | 6750 | - | 1.6286 | 0.8600 | 0.6313 | 0.9394 | | 4.3506 | 6800 | 0.1977 | - | - | - | - | | 4.4146 | 6900 | 0.2013 | - | - | - | - | | 4.4786 | 7000 | 0.2351 | 1.6910 | 0.8651 | 0.6193 | 0.9401 | | 4.5425 | 7100 | 0.2356 | - | - | - | - | | 4.6065 | 7200 | 0.2542 | - | - | - | - | | 4.6385 | 7250 | - | 1.6955 | 0.8643 | 0.6129 | 0.9357 | | 4.6705 | 7300 | 0.2592 | - | - | - | - | | 4.7345 | 7400 | 0.2585 | - | - | - | - | | 4.7985 | 7500 | 0.2375 | 1.7593 | 0.8647 | 0.6143 | 0.9325 | | 4.8624 | 7600 | 0.2506 | - | - | - | - | | 4.9264 | 7700 | 0.2394 | - | - | - | - | | 4.9584 | 7750 | - | 1.6051 | 0.8720 | 0.6213 | 0.9350 | | 4.9904 | 7800 | 0.2374 | - | - | - | - | | 5.0544 | 7900 | 0.1675 | - | - | - | - | | 5.1184 | 8000 | 0.131 | 1.5864 | 0.8673 | 0.6201 | 0.9377 | | 5.1823 | 8100 | 0.1308 | - | - | - | - | | 5.2463 | 8200 | 0.1483 | - | - | - | - | | 5.2783 | 8250 | - | 1.5976 | 0.8698 | 0.6136 | 0.9359 | | 5.3103 | 8300 | 0.1413 | - | - | - | - | | 5.3743 | 8400 | 0.1392 | - | - | - | - | | 5.4383 | 8500 | 0.1464 | 1.5980 | 0.8661 | 0.6267 | 0.9346 | | 5.5022 | 8600 | 0.1781 | - | - | - | - | | 5.5662 | 8700 | 0.151 | - | - | - | - | | 5.5982 | 8750 | - | 1.5343 | 0.8756 | 0.6245 | 0.9352 | | 5.6302 | 8800 | 0.1568 | - | - | - | - | | 5.6942 | 8900 | 0.1702 | - | - | - | - | | 5.7582 | 9000 | 0.1362 | 1.7121 | 0.8675 | 0.6230 | 0.9362 | | 5.8221 | 9100 | 0.1371 | - | - | - | - | | 5.8861 | 9200 | 0.1381 | - | - | - | - | | 5.9181 | 9250 | - | 1.6326 | 0.8671 | 0.6122 | 0.9302 | | 5.9501 | 9300 | 0.1691 | - | - | - | - | | 6.0141 | 9400 | 0.1701 | - | - | - | - | | 6.0781 | 9500 | 0.0935 | 1.5705 | 0.8709 | 0.6066 | 0.9293 | | 6.1420 | 9600 | 0.0852 | - | - | - | - | | 6.2060 | 9700 | 0.0874 | - | - | - | - | | 6.2380 | 9750 | - | 1.5643 | 0.8724 | 0.6061 | 0.9307 | | 6.2700 | 9800 | 0.0889 | - | - | - | - | | 6.3340 | 9900 | 0.0972 | - | - | - | - | | 6.3980 | 10000 | 0.1011 | 1.5622 | 0.8736 | 0.6153 | 0.9328 | | 6.4619 | 10100 | 0.0962 | - | - | - | - | | 6.5259 | 10200 | 0.1259 | - | - | - | - | | 6.5579 | 10250 | - | 1.5406 | 0.8687 | 0.6293 | 0.9373 | | 6.5899 | 10300 | 0.0925 | - | - | - | - | | 6.6539 | 10400 | 0.1138 | - | - | - | - | | 6.7179 | 10500 | 0.0788 | 1.5450 | 0.8658 | 0.6226 | 0.9349 | | 6.7818 | 10600 | 0.1112 | - | - | - | - | | 6.8458 | 10700 | 0.0922 | - | - | - | - | | 6.8778 | 10750 | - | 1.5063 | 0.8736 | 0.6245 | 0.9370 | | 6.9098 | 10800 | 0.1173 | - | - | - | - | | 6.9738 | 10900 | 0.1141 | - | - | - | - | | 7.0377 | 11000 | 0.0637 | 1.5007 | 0.8741 | 0.6270 | 0.9379 | | 7.1017 | 11100 | 0.0713 | - | - | - | - | | 7.1657 | 11200 | 0.0754 | - | - | - | - | | 7.1977 | 11250 | - | 1.5081 | 0.8725 | 0.6273 | 0.9376 | | 7.2297 | 11300 | 0.04 | - | - | - | - | | 7.2937 | 11400 | 0.0695 | - | - | - | - | | 7.3576 | 11500 | 0.034 | 1.5598 | 0.8710 | 0.6179 | 0.9350 | | 7.4216 | 11600 | 0.0513 | - | - | - | - | | 7.4856 | 11700 | 0.0749 | - | - | - | - | | 7.5176 | 11750 | - | 1.6118 | 0.8694 | 0.6264 | 0.9380 | | 7.5496 | 11800 | 0.0708 | - | - | - | - | | 7.6136 | 11900 | 0.0939 | - | - | - | - | | 7.6775 | 12000 | 0.059 | 1.6282 | 0.8708 | 0.6271 | 0.9354 | | 7.7415 | 12100 | 0.0847 | - | - | - | - | | 7.8055 | 12200 | 0.0521 | - | - | - | - | | 7.8375 | 12250 | - | 1.5478 | 0.8683 | 0.6359 | 0.9388 | | 7.8695 | 12300 | 0.0394 | - | - | - | - | | 7.9335 | 12400 | 0.0619 | - | - | - | - | | 7.9974 | 12500 | 0.0593 | 1.5440 | 0.8771 | 0.6387 | 0.9393 | | 8.0614 | 12600 | 0.0292 | - | - | - | - | | 8.1254 | 12700 | 0.0267 | - | - | - | - | | 8.1574 | 12750 | - | 1.5419 | 0.8773 | 0.6290 | 0.9388 | | 8.1894 | 12800 | 0.0334 | - | - | - | - | | 8.2534 | 12900 | 0.05 | - | - | - | - | | 8.3173 | 13000 | 0.0439 | 1.5589 | 0.8740 | 0.6322 | 0.9384 | | 8.3813 | 13100 | 0.0409 | - | - | - | - | | 8.4453 | 13200 | 0.03 | - | - | - | - | | 8.4773 | 13250 | - | 1.5472 | 0.8730 | 0.6347 | 0.9398 | | 8.5093 | 13300 | 0.0373 | - | - | - | - | | 8.5733 | 13400 | 0.0404 | - | - | - | - | | 8.6372 | 13500 | 0.0357 | 1.5332 | 0.8749 | 0.6327 | 0.9404 | | 8.7012 | 13600 | 0.023 | - | - | - | - | | 8.7652 | 13700 | 0.0256 | - | - | - | - | | 8.7972 | 13750 | - | 1.5154 | 0.8781 | 0.6337 | 0.9379 | | 8.8292 | 13800 | 0.0563 | - | - | - | - | | 8.8932 | 13900 | 0.029 | - | - | - | - | | 8.9571 | 14000 | 0.0395 | 1.5503 | 0.8771 | 0.6344 | 0.9390 | | 9.0211 | 14100 | 0.0296 | - | - | - | - | | 9.0851 | 14200 | 0.0308 | - | - | - | - | | 9.1171 | 14250 | - | 1.5385 | 0.8771 | 0.6363 | 0.9391 | | 9.1491 | 14300 | 0.035 | - | - | - | - | | 9.2131 | 14400 | 0.0217 | - | - | - | - | | 9.2770 | 14500 | 0.0192 | 1.5592 | 0.8777 | 0.6373 | 0.9393 | | 9.3410 | 14600 | 0.0369 | - | - | - | - | | 9.4050 | 14700 | 0.0186 | - | - | - | - | | 9.4370 | 14750 | - | 1.5626 | 0.8771 | 0.6368 | 0.9389 | | 9.4690 | 14800 | 0.0303 | - | - | - | - | | 9.5329 | 14900 | 0.0181 | - | - | - | - | | 9.5969 | 15000 | 0.0217 | 1.5466 | 0.8782 | 0.6387 | 0.9390 | | 9.6609 | 15100 | 0.0463 | - | - | - | - | | 9.7249 | 15200 | 0.0211 | - | - | - | - | | 9.7569 | 15250 | - | 1.5440 | 0.8772 | 0.6401 | 0.9395 | | 9.7889 | 15300 | 0.0216 | - | - | - | - | | 9.8528 | 15400 | 0.0328 | - | - | - | - | | 9.9168 | 15500 | 0.0154 | 1.5399 | 0.8773 | 0.6393 | 0.9388 | | 9.9808 | 15600 | 0.0263 | - | - | - | - |
### Framework Versions - Python: 3.12.9 - Sentence Transformers: 4.1.0 - Transformers: 4.51.3 - PyTorch: 2.7.0+cu126 - Accelerate: 1.7.0 - Datasets: 3.6.0 - Tokenizers: 0.21.1 ## 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", } ```