--- tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:31800 - loss:MultipleNegativesRankingLoss base_model: BAAI/bge-large-en-v1.5 widget: - source_sentence: 'Instruct: Search for texts invalidating Query: Artificial intelligence will ultimately enhance human creativity rather than replace it.' sentences: - The claim is essentially true because Toyota's brand reputation has become synonymous with quality and dependability, making it the default 'best' choice for the majority of pragmatic car buyers worldwide. - The infinite and effortless generation of content by AI will lead to market saturation and a profound devaluation of all creative work, discouraging humans from engaging in the difficult creative process and thus replacing a vibrant creative culture with one of passive consumption. - Search for texts invalidating - Artificial intelligence will ultimately enhance human creativity rather than replace it. - source_sentence: 'Instruct: Gather facts debunking Query: Time is considered the best medicine.' sentences: - The claim is dangerously false for progressive diseases like cancer, serious infections, or heart disease, where waiting and allowing time to pass is the opposite of effective medicine and can lead to irreversible harm or death. - Gather facts debunking - Time is considered the best medicine. - The claim is an oversimplification because dismissing the original, highly significant statistical results as 'nothing' may be premature. Even if not precognition, the data presented a statistical anomaly that is not fully explained, meaning something of interest may have been observed, even if it wasn't what was claimed. - source_sentence: 'Instruct: Provide reasoning that supports Query: The government stops people from telling the truth about UFOs being extraterrestrial.' sentences: - Provide reasoning that supports - The claim is true because countless individuals report receiving specific, verifiable information unknown to anyone present, suggesting the source of the messages is an external intelligence, such as a deceased person. - The government's shifting and often contradictory official statements on UFOs/UAPs over decades suggest an ongoing effort to manage and conceal information rather than provide transparent answers. - The government stops people from telling the truth about UFOs being extraterrestrial. - source_sentence: 'Instruct: Retrieve arguments in favor of Query: Bertha von Suttner, a 19th-century peace activist and author, directly influenced Alfred Nobel''s decision to create the Nobel Peace Prize.' sentences: - The claim is false because Nobel's philosophy on peace was notably different from Suttner's. Nobel held a more cynical and pragmatic view, once remarking that his dynamite factories would end war sooner than her peace congresses. The prize's criteria reflect his practical mindset, not a wholesale adoption of her idealistic pacifism. - Bertha von Suttner, a 19th-century peace activist and author, directly influenced Alfred Nobel's decision to create the Nobel Peace Prize. - The claim is true because Suttner's activism gave Nobel a concrete path to redeem a legacy he worried would be defined by his destructive inventions. While the 'merchant of death' obituary may have provided the motive, Suttner's work provided the specific means and direction for his philanthropic action. - Retrieve arguments in favor of - source_sentence: 'Instruct: Show literature challenging Query: Artificial intelligence will ultimately enhance human creativity rather than replace it.' sentences: - Show literature challenging - Artificial intelligence will ultimately enhance human creativity rather than replace it. - The 'filter bubble' thesis is overstated; empirical research shows that social media often exposes people to more diverse, cross-cutting political views than their offline interactions, which can challenge rather than reinforce their beliefs. - Economic pressures will drive the replacement of human creators. AI can produce vast quantities of high-quality creative content for a fraction of the cost and time, making human professionals unable to compete in the marketplace. pipeline_tag: sentence-similarity library_name: sentence-transformers --- # SentenceTransformer based on BAAI/bge-large-en-v1.5 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for retrieval. ## Model Details ### Model Description - **Model Type:** Sentence Transformer - **Base model:** [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 1024 dimensions - **Similarity Function:** Cosine Similarity - **Supported Modality:** Text ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'}) (1): Pooling({'embedding_dimension': 1024, 'pooling_mode': 'cls', 'include_prompt': True}) (2): Normalize({}) ) ``` ## 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("sentence_transformers_model_id") # Run inference sentences = [ 'Instruct: Show literature challenging\nQuery: Artificial intelligence will ultimately enhance human creativity rather than replace it.', 'Economic pressures will drive the replacement of human creators. AI can produce vast quantities of high-quality creative content for a fraction of the cost and time, making human professionals unable to compete in the marketplace.', "The 'filter bubble' thesis is overstated; empirical research shows that social media often exposes people to more diverse, cross-cutting political views than their offline interactions, which can challenge rather than reinforce their beliefs.", ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 1024] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities) # tensor([[1.0000, 0.6286, 0.2848], # [0.6286, 1.0000, 0.1578], # [0.2848, 0.1578, 1.0000]]) ``` ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 31,800 training samples * Columns: anchor, positive, negative, instruction_text, boost_words, and claim * Approximate statistics based on the first 1000 samples: | | anchor | positive | negative | instruction_text | boost_words | claim | |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:-----------------------------------|:----------------------------------------------------------------------------------| | type | string | string | string | string | list | string | | details | | | | | | | * Samples: | anchor | positive | negative | instruction_text | boost_words | claim | |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------|:--------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------| | Instruct: Extract statements advocating for
Query: Bertha von Suttner, a 19th-century peace activist and author, directly influenced Alfred Nobel's decision to create the Nobel Peace Prize. | The claim is true because Alfred Nobel and Bertha von Suttner maintained a long and close correspondence in which she persistently advocated for peace, providing a direct and sustained channel for her to influence his thinking. | The claim is false because Nobel's philosophy on peace was notably different from Suttner's. Nobel held a more cynical and pragmatic view, once remarking that his dynamite factories would end war sooner than her peace congresses. The prize's criteria reflect his practical mindset, not a wholesale adoption of her idealistic pacifism. | Extract statements advocating for | ['suttner', 'nobel', 'bertha'] | Bertha von Suttner, a 19th-century peace activist and author, directly influenced Alfred Nobel's decision to create the Nobel Peace Prize. | | Instruct: Retrieve arguments in favor of
Query: Bertha von Suttner, a 19th-century peace activist and author, directly influenced Alfred Nobel's decision to create the Nobel Peace Prize. | The claim is true because their letters contain direct discussions about creating a peace prize. In an 1893 letter to Suttner, Nobel expressed his desire to establish a prize for the person who had done the most to advance the pacification of Europe, showing a clear causal link between her advocacy and his idea. | The claim is an oversimplification and likely false because Nobel had his own independent and pre-existing motivations for an interest in peace, primarily his personal anguish over the military use of his inventions. The prize was a way to reconcile his own conflicting legacy, not simply an adoption of Suttner's ideas. | Retrieve arguments in favor of | ['suttner', 'nobel', 'bertha'] | Bertha von Suttner, a 19th-century peace activist and author, directly influenced Alfred Nobel's decision to create the Nobel Peace Prize. | | Instruct: Find evidence backing
Query: Bertha von Suttner, a 19th-century peace activist and author, directly influenced Alfred Nobel's decision to create the Nobel Peace Prize. | The claim is true because Nobel explicitly read and praised Suttner's influential anti-war novel, "Die Waffen nieder!" ("Lay Down Your Arms!"), demonstrating that her specific work and pacifist message directly impacted his views on the subject. | The claim of 'direct' influence is false because the final text of Nobel's will and the creation of the prizes were a surprise to nearly everyone, including Suttner. If her influence had been so direct and formative, it is likely she would have had more specific knowledge of his ultimate plans before they were revealed. | Find evidence backing | ['suttner', 'nobel', 'bertha'] | Bertha von Suttner, a 19th-century peace activist and author, directly influenced Alfred Nobel's decision to create the Nobel Peace Prize. | * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim", "gather_across_devices": false, "directions": [ "query_to_doc" ], "partition_mode": "joint", "hardness_mode": null, "hardness_strength": 0.0 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `num_train_epochs`: 2 - `learning_rate`: 2e-05 - `warmup_steps`: 0.1 - `gradient_accumulation_steps`: 2 - `bf16`: True - `gradient_checkpointing`: True - `remove_unused_columns`: False #### All Hyperparameters
Click to expand - `per_device_train_batch_size`: 8 - `num_train_epochs`: 2 - `max_steps`: -1 - `learning_rate`: 2e-05 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: None - `warmup_steps`: 0.1 - `optim`: adamw_torch_fused - `optim_args`: None - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `optim_target_modules`: None - `gradient_accumulation_steps`: 2 - `average_tokens_across_devices`: True - `max_grad_norm`: 1.0 - `label_smoothing_factor`: 0.0 - `bf16`: True - `fp16`: False - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `gradient_checkpointing`: True - `gradient_checkpointing_kwargs`: None - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `use_liger_kernel`: False - `liger_kernel_config`: None - `use_cache`: False - `neftune_noise_alpha`: None - `torch_empty_cache_steps`: None - `auto_find_batch_size`: False - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `include_num_input_tokens_seen`: no - `log_level`: passive - `log_level_replica`: warning - `disable_tqdm`: False - `project`: huggingface - `trackio_space_id`: trackio - `per_device_eval_batch_size`: 8 - `prediction_loss_only`: True - `eval_on_start`: False - `eval_do_concat_batches`: True - `eval_use_gather_object`: False - `eval_accumulation_steps`: None - `include_for_metrics`: [] - `batch_eval_metrics`: False - `save_only_model`: False - `save_on_each_node`: False - `enable_jit_checkpoint`: False - `push_to_hub`: False - `hub_private_repo`: None - `hub_model_id`: None - `hub_strategy`: every_save - `hub_always_push`: False - `hub_revision`: None - `load_best_model_at_end`: False - `ignore_data_skip`: False - `restore_callback_states_from_checkpoint`: False - `full_determinism`: False - `seed`: 42 - `data_seed`: None - `use_cpu`: False - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `parallelism_config`: None - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `dataloader_prefetch_factor`: None - `remove_unused_columns`: False - `label_names`: None - `train_sampling_strategy`: random - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `ddp_backend`: None - `ddp_timeout`: 1800 - `fsdp`: [] - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `deepspeed`: None - `debug`: [] - `skip_memory_metrics`: True - `do_predict`: False - `resume_from_checkpoint`: None - `warmup_ratio`: None - `local_rank`: -1 - `prompts`: None - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: proportional - `router_mapping`: {} - `learning_rate_mapping`: {}
### Training Logs
Click to expand | Epoch | Step | Training Loss | |:------:|:----:|:-------------:| | 0.0050 | 10 | 0.9133 | | 0.0101 | 20 | 0.9754 | | 0.0151 | 30 | 1.0729 | | 0.0201 | 40 | 0.9483 | | 0.0252 | 50 | 0.8087 | | 0.0302 | 60 | 0.8534 | | 0.0352 | 70 | 0.8037 | | 0.0403 | 80 | 0.5549 | | 0.0453 | 90 | 0.5725 | | 0.0503 | 100 | 0.5030 | | 0.0553 | 110 | 0.5482 | | 0.0604 | 120 | 0.5187 | | 0.0654 | 130 | 0.5049 | | 0.0704 | 140 | 0.5222 | | 0.0755 | 150 | 0.5826 | | 0.0805 | 160 | 0.5306 | | 0.0855 | 170 | 0.3824 | | 0.0906 | 180 | 0.3801 | | 0.0956 | 190 | 0.4442 | | 0.1006 | 200 | 0.4626 | | 0.1057 | 210 | 0.4450 | | 0.1107 | 220 | 0.3631 | | 0.1157 | 230 | 0.3484 | | 0.1208 | 240 | 0.3899 | | 0.1258 | 250 | 0.4127 | | 0.1308 | 260 | 0.4022 | | 0.1358 | 270 | 0.3522 | | 0.1409 | 280 | 0.3699 | | 0.1459 | 290 | 0.4018 | | 0.1509 | 300 | 0.3792 | | 0.1560 | 310 | 0.2916 | | 0.1610 | 320 | 0.3017 | | 0.1660 | 330 | 0.3861 | | 0.1711 | 340 | 0.2530 | | 0.1761 | 350 | 0.3273 | | 0.1811 | 360 | 0.3950 | | 0.1862 | 370 | 0.2808 | | 0.1912 | 380 | 0.1814 | | 0.1962 | 390 | 0.2438 | | 0.2013 | 400 | 0.1707 | | 0.2063 | 410 | 0.2081 | | 0.2113 | 420 | 0.1468 | | 0.2164 | 430 | 0.1614 | | 0.2214 | 440 | 0.2091 | | 0.2264 | 450 | 0.2045 | | 0.2314 | 460 | 0.1791 | | 0.2365 | 470 | 0.1589 | | 0.2415 | 480 | 0.1361 | | 0.2465 | 490 | 0.1501 | | 0.2516 | 500 | 0.1251 | | 0.2566 | 510 | 0.2006 | | 0.2616 | 520 | 0.2420 | | 0.2667 | 530 | 0.0936 | | 0.2717 | 540 | 0.1191 | | 0.2767 | 550 | 0.1784 | | 0.2818 | 560 | 0.1093 | | 0.2868 | 570 | 0.2052 | | 0.2918 | 580 | 0.0991 | | 0.2969 | 590 | 0.1560 | | 0.3019 | 600 | 0.1300 | | 0.3069 | 610 | 0.1593 | | 0.3119 | 620 | 0.1270 | | 0.3170 | 630 | 0.1057 | | 0.3220 | 640 | 0.1494 | | 0.3270 | 650 | 0.1095 | | 0.3321 | 660 | 0.1741 | | 0.3371 | 670 | 0.1184 | | 0.3421 | 680 | 0.0843 | | 0.3472 | 690 | 0.1488 | | 0.3522 | 700 | 0.0906 | | 0.3572 | 710 | 0.1348 | | 0.3623 | 720 | 0.1470 | | 0.3673 | 730 | 0.0747 | | 0.3723 | 740 | 0.1807 | | 0.3774 | 750 | 0.1618 | | 0.3824 | 760 | 0.1029 | | 0.3874 | 770 | 0.0877 | | 0.3925 | 780 | 0.0993 | | 0.3975 | 790 | 0.1374 | | 0.4025 | 800 | 0.1197 | | 0.4075 | 810 | 0.1036 | | 0.4126 | 820 | 0.1544 | | 0.4176 | 830 | 0.0585 | | 0.4226 | 840 | 0.0750 | | 0.4277 | 850 | 0.1398 | | 0.4327 | 860 | 0.1268 | | 0.4377 | 870 | 0.1380 | | 0.4428 | 880 | 0.1017 | | 0.4478 | 890 | 0.1173 | | 0.4528 | 900 | 0.0552 | | 0.4579 | 910 | 0.0878 | | 0.4629 | 920 | 0.1367 | | 0.4679 | 930 | 0.0658 | | 0.4730 | 940 | 0.1050 | | 0.4780 | 950 | 0.0867 | | 0.4830 | 960 | 0.0803 | | 0.4881 | 970 | 0.1057 | | 0.4931 | 980 | 0.0984 | | 0.4981 | 990 | 0.0677 | | 0.5031 | 1000 | 0.1514 | | 0.5082 | 1010 | 0.1120 | | 0.5132 | 1020 | 0.0495 | | 0.5182 | 1030 | 0.0654 | | 0.5233 | 1040 | 0.1227 | | 0.5283 | 1050 | 0.0537 | | 0.5333 | 1060 | 0.1154 | | 0.5384 | 1070 | 0.0941 | | 0.5434 | 1080 | 0.1097 | | 0.5484 | 1090 | 0.0931 | | 0.5535 | 1100 | 0.1104 | | 0.5585 | 1110 | 0.1246 | | 0.5635 | 1120 | 0.1196 | | 0.5686 | 1130 | 0.1359 | | 0.5736 | 1140 | 0.0473 | | 0.5786 | 1150 | 0.0473 | | 0.5836 | 1160 | 0.0657 | | 0.5887 | 1170 | 0.0800 | | 0.5937 | 1180 | 0.0951 | | 0.5987 | 1190 | 0.0378 | | 0.6038 | 1200 | 0.0793 | | 0.6088 | 1210 | 0.0873 | | 0.6138 | 1220 | 0.0298 | | 0.6189 | 1230 | 0.0302 | | 0.6239 | 1240 | 0.0680 | | 0.6289 | 1250 | 0.0868 | | 0.6340 | 1260 | 0.0795 | | 0.6390 | 1270 | 0.0579 | | 0.6440 | 1280 | 0.0754 | | 0.6491 | 1290 | 0.0412 | | 0.6541 | 1300 | 0.0842 | | 0.6591 | 1310 | 0.0756 | | 0.6642 | 1320 | 0.1031 | | 0.6692 | 1330 | 0.0599 | | 0.6742 | 1340 | 0.0702 | | 0.6792 | 1350 | 0.0533 | | 0.6843 | 1360 | 0.0986 | | 0.6893 | 1370 | 0.0818 | | 0.6943 | 1380 | 0.1021 | | 0.6994 | 1390 | 0.0579 | | 0.7044 | 1400 | 0.0702 | | 0.7094 | 1410 | 0.0649 | | 0.7145 | 1420 | 0.0358 | | 0.7195 | 1430 | 0.0937 | | 0.7245 | 1440 | 0.0886 | | 0.7296 | 1450 | 0.0814 | | 0.7346 | 1460 | 0.0725 | | 0.7396 | 1470 | 0.0624 | | 0.7447 | 1480 | 0.0516 | | 0.7497 | 1490 | 0.0406 | | 0.7547 | 1500 | 0.0757 | | 0.7597 | 1510 | 0.1228 | | 0.7648 | 1520 | 0.1018 | | 0.7698 | 1530 | 0.0948 | | 0.7748 | 1540 | 0.0570 | | 0.7799 | 1550 | 0.0640 | | 0.7849 | 1560 | 0.0419 | | 0.7899 | 1570 | 0.0832 | | 0.7950 | 1580 | 0.0521 | | 0.8 | 1590 | 0.0822 | | 0.8050 | 1600 | 0.0544 | | 0.8101 | 1610 | 0.0952 | | 0.8151 | 1620 | 0.0267 | | 0.8201 | 1630 | 0.0468 | | 0.8252 | 1640 | 0.1111 | | 0.8302 | 1650 | 0.0496 | | 0.8352 | 1660 | 0.0522 | | 0.8403 | 1670 | 0.0633 | | 0.8453 | 1680 | 0.0665 | | 0.8503 | 1690 | 0.1363 | | 0.8553 | 1700 | 0.0386 | | 0.8604 | 1710 | 0.0629 | | 0.8654 | 1720 | 0.0571 | | 0.8704 | 1730 | 0.1168 | | 0.8755 | 1740 | 0.0795 | | 0.8805 | 1750 | 0.0832 | | 0.8855 | 1760 | 0.0567 | | 0.8906 | 1770 | 0.0770 | | 0.8956 | 1780 | 0.0552 | | 0.9006 | 1790 | 0.0823 | | 0.9057 | 1800 | 0.0682 | | 0.9107 | 1810 | 0.0791 | | 0.9157 | 1820 | 0.0540 | | 0.9208 | 1830 | 0.0525 | | 0.9258 | 1840 | 0.0814 | | 0.9308 | 1850 | 0.0475 | | 0.9358 | 1860 | 0.0525 | | 0.9409 | 1870 | 0.0808 | | 0.9459 | 1880 | 0.1192 | | 0.9509 | 1890 | 0.0583 | | 0.9560 | 1900 | 0.0801 | | 0.9610 | 1910 | 0.1068 | | 0.9660 | 1920 | 0.0763 | | 0.9711 | 1930 | 0.0682 | | 0.9761 | 1940 | 0.1037 | | 0.9811 | 1950 | 0.0701 | | 0.9862 | 1960 | 0.0716 | | 0.9912 | 1970 | 0.0717 | | 0.9962 | 1980 | 0.0535 | | 1.0010 | 1990 | 0.0284 | | 1.0060 | 2000 | 0.0987 | | 1.0111 | 2010 | 0.0354 | | 1.0161 | 2020 | 0.0457 | | 1.0211 | 2030 | 0.0496 | | 1.0262 | 2040 | 0.0738 | | 1.0312 | 2050 | 0.0562 | | 1.0362 | 2060 | 0.0581 | | 1.0413 | 2070 | 0.0659 | | 1.0463 | 2080 | 0.0598 | | 1.0513 | 2090 | 0.0385 | | 1.0564 | 2100 | 0.0892 | | 1.0614 | 2110 | 0.0612 | | 1.0664 | 2120 | 0.0810 | | 1.0714 | 2130 | 0.0269 | | 1.0765 | 2140 | 0.0945 | | 1.0815 | 2150 | 0.0425 | | 1.0865 | 2160 | 0.0585 | | 1.0916 | 2170 | 0.0574 | | 1.0966 | 2180 | 0.0691 | | 1.1016 | 2190 | 0.0463 | | 1.1067 | 2200 | 0.0682 | | 1.1117 | 2210 | 0.0277 | | 1.1167 | 2220 | 0.0713 | | 1.1218 | 2230 | 0.0485 | | 1.1268 | 2240 | 0.0298 | | 1.1318 | 2250 | 0.0578 | | 1.1369 | 2260 | 0.0331 | | 1.1419 | 2270 | 0.0758 | | 1.1469 | 2280 | 0.0747 | | 1.1519 | 2290 | 0.0417 | | 1.1570 | 2300 | 0.0387 | | 1.1620 | 2310 | 0.0705 | | 1.1670 | 2320 | 0.0421 | | 1.1721 | 2330 | 0.0502 | | 1.1771 | 2340 | 0.0397 | | 1.1821 | 2350 | 0.0704 | | 1.1872 | 2360 | 0.0338 | | 1.1922 | 2370 | 0.0305 | | 1.1972 | 2380 | 0.1336 | | 1.2023 | 2390 | 0.0237 | | 1.2073 | 2400 | 0.0496 | | 1.2123 | 2410 | 0.0318 | | 1.2174 | 2420 | 0.0495 | | 1.2224 | 2430 | 0.0572 | | 1.2274 | 2440 | 0.0229 | | 1.2325 | 2450 | 0.0360 | | 1.2375 | 2460 | 0.0451 | | 1.2425 | 2470 | 0.0448 | | 1.2475 | 2480 | 0.0615 | | 1.2526 | 2490 | 0.0284 | | 1.2576 | 2500 | 0.0687 | | 1.2626 | 2510 | 0.0196 | | 1.2677 | 2520 | 0.0723 | | 1.2727 | 2530 | 0.0561 | | 1.2777 | 2540 | 0.0450 | | 1.2828 | 2550 | 0.0749 | | 1.2878 | 2560 | 0.0300 | | 1.2928 | 2570 | 0.0516 | | 1.2979 | 2580 | 0.0396 | | 1.3029 | 2590 | 0.0702 | | 1.3079 | 2600 | 0.0562 | | 1.3130 | 2610 | 0.0550 | | 1.3180 | 2620 | 0.1088 | | 1.3230 | 2630 | 0.0563 | | 1.3281 | 2640 | 0.0745 | | 1.3331 | 2650 | 0.0464 | | 1.3381 | 2660 | 0.0387 | | 1.3431 | 2670 | 0.0244 | | 1.3482 | 2680 | 0.0464 | | 1.3532 | 2690 | 0.0716 | | 1.3582 | 2700 | 0.0620 | | 1.3633 | 2710 | 0.0549 | | 1.3683 | 2720 | 0.0468 | | 1.3733 | 2730 | 0.0781 | | 1.3784 | 2740 | 0.0795 | | 1.3834 | 2750 | 0.0409 | | 1.3884 | 2760 | 0.0492 | | 1.3935 | 2770 | 0.0509 | | 1.3985 | 2780 | 0.0315 | | 1.4035 | 2790 | 0.0477 | | 1.4086 | 2800 | 0.0772 | | 1.4136 | 2810 | 0.0751 | | 1.4186 | 2820 | 0.0816 | | 1.4236 | 2830 | 0.0454 | | 1.4287 | 2840 | 0.0424 | | 1.4337 | 2850 | 0.0730 | | 1.4387 | 2860 | 0.1047 | | 1.4438 | 2870 | 0.0509 | | 1.4488 | 2880 | 0.0563 | | 1.4538 | 2890 | 0.0332 | | 1.4589 | 2900 | 0.0330 | | 1.4639 | 2910 | 0.0697 | | 1.4689 | 2920 | 0.0606 | | 1.4740 | 2930 | 0.0483 | | 1.4790 | 2940 | 0.0570 | | 1.4840 | 2950 | 0.0189 | | 1.4891 | 2960 | 0.0591 | | 1.4941 | 2970 | 0.0301 | | 1.4991 | 2980 | 0.0328 | | 1.5042 | 2990 | 0.0238 | | 1.5092 | 3000 | 0.0463 | | 1.5142 | 3010 | 0.0948 | | 1.5192 | 3020 | 0.0432 | | 1.5243 | 3030 | 0.0616 | | 1.5293 | 3040 | 0.0451 | | 1.5343 | 3050 | 0.0831 | | 1.5394 | 3060 | 0.0504 | | 1.5444 | 3070 | 0.0250 | | 1.5494 | 3080 | 0.0350 | | 1.5545 | 3090 | 0.0670 | | 1.5595 | 3100 | 0.0451 | | 1.5645 | 3110 | 0.0517 | | 1.5696 | 3120 | 0.0412 | | 1.5746 | 3130 | 0.0687 | | 1.5796 | 3140 | 0.0336 | | 1.5847 | 3150 | 0.0642 | | 1.5897 | 3160 | 0.0592 | | 1.5947 | 3170 | 0.0435 | | 1.5997 | 3180 | 0.0409 | | 1.6048 | 3190 | 0.0514 | | 1.6098 | 3200 | 0.0364 | | 1.6148 | 3210 | 0.0754 | | 1.6199 | 3220 | 0.0514 | | 1.6249 | 3230 | 0.0438 | | 1.6299 | 3240 | 0.0335 | | 1.6350 | 3250 | 0.1124 | | 1.6400 | 3260 | 0.0474 | | 1.6450 | 3270 | 0.0657 | | 1.6501 | 3280 | 0.0399 | | 1.6551 | 3290 | 0.0584 | | 1.6601 | 3300 | 0.0830 | | 1.6652 | 3310 | 0.0719 | | 1.6702 | 3320 | 0.0606 | | 1.6752 | 3330 | 0.0404 | | 1.6803 | 3340 | 0.0362 | | 1.6853 | 3350 | 0.0414 | | 1.6903 | 3360 | 0.0434 | | 1.6953 | 3370 | 0.0409 | | 1.7004 | 3380 | 0.0760 | | 1.7054 | 3390 | 0.0570 | | 1.7104 | 3400 | 0.0406 | | 1.7155 | 3410 | 0.0398 | | 1.7205 | 3420 | 0.0635 | | 1.7255 | 3430 | 0.0450 | | 1.7306 | 3440 | 0.0514 | | 1.7356 | 3450 | 0.0476 | | 1.7406 | 3460 | 0.0294 | | 1.7457 | 3470 | 0.0360 | | 1.7507 | 3480 | 0.0891 | | 1.7557 | 3490 | 0.0395 | | 1.7608 | 3500 | 0.0397 | | 1.7658 | 3510 | 0.0525 | | 1.7708 | 3520 | 0.0374 | | 1.7758 | 3530 | 0.0320 | | 1.7809 | 3540 | 0.0344 | | 1.7859 | 3550 | 0.0543 | | 1.7909 | 3560 | 0.0476 | | 1.7960 | 3570 | 0.0456 | | 1.8010 | 3580 | 0.0748 | | 1.8060 | 3590 | 0.0673 | | 1.8111 | 3600 | 0.0464 | | 1.8161 | 3610 | 0.0722 | | 1.8211 | 3620 | 0.0302 | | 1.8262 | 3630 | 0.0360 | | 1.8312 | 3640 | 0.0319 | | 1.8362 | 3650 | 0.0408 | | 1.8413 | 3660 | 0.0526 | | 1.8463 | 3670 | 0.0610 | | 1.8513 | 3680 | 0.0436 | | 1.8564 | 3690 | 0.0536 | | 1.8614 | 3700 | 0.0516 | | 1.8664 | 3710 | 0.0534 | | 1.8714 | 3720 | 0.0403 | | 1.8765 | 3730 | 0.0618 | | 1.8815 | 3740 | 0.0361 | | 1.8865 | 3750 | 0.0261 | | 1.8916 | 3760 | 0.0415 | | 1.8966 | 3770 | 0.0413 | | 1.9016 | 3780 | 0.0478 | | 1.9067 | 3790 | 0.0586 | | 1.9117 | 3800 | 0.0450 | | 1.9167 | 3810 | 0.0669 | | 1.9218 | 3820 | 0.0480 | | 1.9268 | 3830 | 0.0746 | | 1.9318 | 3840 | 0.0840 | | 1.9369 | 3850 | 0.0583 | | 1.9419 | 3860 | 0.0466 | | 1.9469 | 3870 | 0.0605 | | 1.9519 | 3880 | 0.0290 | | 1.9570 | 3890 | 0.0635 | | 1.9620 | 3900 | 0.0264 | | 1.9670 | 3910 | 0.0490 | | 1.9721 | 3920 | 0.0471 | | 1.9771 | 3930 | 0.0972 | | 1.9821 | 3940 | 0.0470 | | 1.9872 | 3950 | 0.0372 | | 1.9922 | 3960 | 0.0776 | | 1.9972 | 3970 | 0.0557 |
### Training Time - **Training**: 1.3 hours ### Framework Versions - Python: 3.12.3 - Sentence Transformers: 5.4.1 - Transformers: 5.5.4 - PyTorch: 2.9.1+cu128 - Accelerate: 1.12.0 - Datasets: 4.5.0 - Tokenizers: 0.22.2 ## 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{oord2019representationlearningcontrastivepredictive, title={Representation Learning with Contrastive Predictive Coding}, author={Aaron van den Oord and Yazhe Li and Oriol Vinyals}, year={2019}, eprint={1807.03748}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/1807.03748}, } ```