--- tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:449904 - loss:CosineSimilarityLoss base_model: CocoRoF/ModernBERT-SimCSE-multitask_v03-retry widget: - source_sentence: 우리는 움직이는 동행 우주 정지 좌표계에 비례하여 이동하고 있습니다 ... 약 371km / s에서 별자리 leo 쪽으로. " sentences: - 두 마리의 독수리가 가지에 앉는다. - 다른 물체와는 관련이 없는 '정지'는 없다. - 소녀는 버스의 열린 문 앞에 서 있다. - source_sentence: 숲에는 개들이 있다. sentences: - 양을 보는 아이들. - 여왕의 배우자를 "왕"이라고 부르지 않는 것은 아주 좋은 이유가 있다. 왜냐하면 그들은 왕이 아니기 때문이다. - 개들은 숲속에 혼자 있다. - source_sentence: '첫째, 두 가지 다른 종류의 대시가 있다는 것을 알아야 합니다 : en 대시와 em 대시.' sentences: - 그들은 그 물건들을 집 주변에 두고 가거나 집의 정리를 해칠 의도가 없다. - 세미콜론은 혼자 있을 수 있는 문장에 참여하는데 사용되지만, 그들의 관계를 강조하기 위해 결합됩니다. - 그의 남동생이 지켜보는 동안 집 앞에서 트럼펫을 연주하는 금발의 아이. - source_sentence: 한 여성이 생선 껍질을 벗기고 있다. sentences: - 한 남자가 수영장으로 뛰어들었다. - 한 여성이 프라이팬에 노란 혼합물을 부어 넣고 있다. - 두 마리의 갈색 개가 눈 속에서 서로 놀고 있다. - source_sentence: 버스가 바쁜 길을 따라 운전한다. sentences: - 우리와 같은 태양계가 은하계 밖에서 존재할 수도 있을 것입니다. - 그 여자는 데이트하러 가는 중이다. - 녹색 버스가 도로를 따라 내려간다. datasets: - x2bee/misc_sts_pairs_v2_kor_kosimcse pipeline_tag: sentence-similarity library_name: sentence-transformers metrics: - pearson_cosine - spearman_cosine - pearson_euclidean - spearman_euclidean - pearson_manhattan - spearman_manhattan - pearson_dot - spearman_dot - pearson_max - spearman_max model-index: - name: SentenceTransformer based on CocoRoF/ModernBERT-SimCSE-multitask_v03-retry results: - task: type: semantic-similarity name: Semantic Similarity dataset: name: sts dev type: sts_dev metrics: - type: pearson_cosine value: 0.8220874775898197 name: Pearson Cosine - type: spearman_cosine value: 0.8282368218808581 name: Spearman Cosine - type: pearson_euclidean value: 0.7929031352092236 name: Pearson Euclidean - type: spearman_euclidean value: 0.7979913252239026 name: Spearman Euclidean - type: pearson_manhattan value: 0.7936882861676204 name: Pearson Manhattan - type: spearman_manhattan value: 0.7996541111809876 name: Spearman Manhattan - type: pearson_dot value: 0.7010536213435227 name: Pearson Dot - type: spearman_dot value: 0.6844746263331734 name: Spearman Dot - type: pearson_max value: 0.8220874775898197 name: Pearson Max - type: spearman_max value: 0.8282368218808581 name: Spearman Max --- # SentenceTransformer based on CocoRoF/ModernBERT-SimCSE-multitask_v03-retry This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [CocoRoF/ModernBERT-SimCSE-multitask_v03-retry](https://huggingface.co/CocoRoF/ModernBERT-SimCSE-multitask_v03-retry) on the [misc_sts_pairs_v2_kor_kosimcse](https://huggingface.co/datasets/x2bee/misc_sts_pairs_v2_kor_kosimcse) dataset. It maps sentences & paragraphs to a 1024-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:** [CocoRoF/ModernBERT-SimCSE-multitask_v03-retry](https://huggingface.co/CocoRoF/ModernBERT-SimCSE-multitask_v03-retry) - **Maximum Sequence Length:** 2048 tokens - **Output Dimensionality:** 1024 dimensions - **Similarity Function:** Cosine Similarity - **Training Dataset:** - [misc_sts_pairs_v2_kor_kosimcse](https://huggingface.co/datasets/x2bee/misc_sts_pairs_v2_kor_kosimcse) ### 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': 2048, 'do_lower_case': False}) with Transformer model: ModernBertModel (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}) (2): Dense({'in_features': 768, 'out_features': 1024, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'}) ) ``` ## 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("CocoRoF/ModernBERT-SimCSE-multitask_v03-distill") # Run inference sentences = [ '버스가 바쁜 길을 따라 운전한다.', '녹색 버스가 도로를 따라 내려간다.', '그 여자는 데이트하러 가는 중이다.', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 1024] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` ## Evaluation ### Metrics #### Semantic Similarity * Dataset: `sts_dev` * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:-------------------|:-----------| | pearson_cosine | 0.8221 | | spearman_cosine | 0.8282 | | pearson_euclidean | 0.7929 | | spearman_euclidean | 0.798 | | pearson_manhattan | 0.7937 | | spearman_manhattan | 0.7997 | | pearson_dot | 0.7011 | | spearman_dot | 0.6845 | | pearson_max | 0.8221 | | **spearman_max** | **0.8282** | ## Training Details ### Training Dataset #### misc_sts_pairs_v2_kor_kosimcse * Dataset: [misc_sts_pairs_v2_kor_kosimcse](https://huggingface.co/datasets/x2bee/misc_sts_pairs_v2_kor_kosimcse) at [e747415](https://huggingface.co/datasets/x2bee/misc_sts_pairs_v2_kor_kosimcse/tree/e747415cfe9ff51d1c1550b8a07e5014c01dea59) * Size: 449,904 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 | |:-------------------------------------------------|:-------------------------------------------|:--------------------------------| | 주홍글씨는 언제 출판되었습니까? | 《주홍글씨》는 몇 년에 출판되었습니까? | 0.8638778924942017 | | 폴란드에서 빨간색과 흰색은 무엇을 의미합니까? | 폴란드 국기의 색상은 무엇입니까? | 0.6773715019226074 | | 노르만인들은 방어를 위해 모트와 베일리 성을 어떻게 사용했는가? | 11세기에는 어떻게 모트와 베일리 성을 만들었습니까? | 0.7460665702819824 | * Loss: [CosineSimilarityLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters: ```json { "loss_fct": "torch.nn.modules.loss.MSELoss" } ``` ### Evaluation Dataset #### Unnamed Dataset * Size: 1,500 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 | |:-------------------------------------|:------------------------------------|:------------------| | 안전모를 가진 한 남자가 춤을 추고 있다. | 안전모를 쓴 한 남자가 춤을 추고 있다. | 1.0 | | 어린아이가 말을 타고 있다. | 아이가 말을 타고 있다. | 0.95 | | 한 남자가 뱀에게 쥐를 먹이고 있다. | 남자가 뱀에게 쥐를 먹이고 있다. | 1.0 | * Loss: [CosineSimilarityLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters: ```json { "loss_fct": "torch.nn.modules.loss.MSELoss" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `overwrite_output_dir`: True - `eval_strategy`: steps - `gradient_accumulation_steps`: 16 - `learning_rate`: 8e-05 - `num_train_epochs`: 10.0 - `warmup_ratio`: 0.2 - `push_to_hub`: True - `hub_model_id`: CocoRoF/ModernBERT-SimCSE-multitask_v03-distill - `hub_strategy`: checkpoint - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `overwrite_output_dir`: True - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 8 - `per_device_eval_batch_size`: 8 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 16 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 8e-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`: 10.0 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `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`: 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`: False - `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`: True - `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`: CocoRoF/ModernBERT-SimCSE-multitask_v03-distill - `hub_strategy`: checkpoint - `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 - `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 - `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 | sts_dev_spearman_max | |:------:|:----:|:-------------:|:---------------:|:--------------------:| | 0.0228 | 10 | 0.3524 | - | - | | 0.0455 | 20 | 0.3496 | - | - | | 0.0683 | 30 | 0.3515 | - | - | | 0.0911 | 40 | 0.348 | - | - | | 0.1138 | 50 | 0.3409 | - | - | | 0.1366 | 60 | 0.347 | - | - | | 0.1593 | 70 | 0.3377 | - | - | | 0.1821 | 80 | 0.3317 | - | - | | 0.2049 | 90 | 0.3279 | - | - | | 0.2276 | 100 | 0.3264 | - | - | | 0.2504 | 110 | 0.3116 | - | - | | 0.2732 | 120 | 0.3055 | - | - | | 0.2959 | 130 | 0.3042 | - | - | | 0.3187 | 140 | 0.2928 | - | - | | 0.3414 | 150 | 0.2835 | - | - | | 0.3642 | 160 | 0.2665 | - | - | | 0.3870 | 170 | 0.2665 | - | - | | 0.4097 | 180 | 0.2486 | - | - | | 0.4325 | 190 | 0.2387 | - | - | | 0.4553 | 200 | 0.2283 | - | - | | 0.4780 | 210 | 0.2237 | - | - | | 0.5008 | 220 | 0.2204 | - | - | | 0.5235 | 230 | 0.205 | - | - | | 0.5463 | 240 | 0.2002 | - | - | | 0.5691 | 250 | 0.1904 | 0.0330 | 0.7921 | | 0.5918 | 260 | 0.1834 | - | - | | 0.6146 | 270 | 0.1776 | - | - | | 0.6374 | 280 | 0.1665 | - | - | | 0.6601 | 290 | 0.1625 | - | - | | 0.6829 | 300 | 0.1585 | - | - | | 0.7056 | 310 | 0.1522 | - | - | | 0.7284 | 320 | 0.1552 | - | - | | 0.7512 | 330 | 0.1448 | - | - | | 0.7739 | 340 | 0.1428 | - | - | | 0.7967 | 350 | 0.1401 | - | - | | 0.8195 | 360 | 0.1399 | - | - | | 0.8422 | 370 | 0.1389 | - | - | | 0.8650 | 380 | 0.1372 | - | - | | 0.8878 | 390 | 0.1338 | - | - | | 0.9105 | 400 | 0.1361 | - | - | | 0.9333 | 410 | 0.1389 | - | - | | 0.9560 | 420 | 0.1328 | - | - | | 0.9788 | 430 | 0.1375 | - | - | | 1.0 | 440 | 0.1266 | - | - | | 1.0228 | 450 | 0.1269 | - | - | | 1.0455 | 460 | 0.1262 | - | - | | 1.0683 | 470 | 0.127 | - | - | | 1.0911 | 480 | 0.1306 | - | - | | 1.1138 | 490 | 0.1266 | - | - | | 1.1366 | 500 | 0.1247 | 0.0405 | 0.7995 | | 1.1593 | 510 | 0.1258 | - | - | | 1.1821 | 520 | 0.1277 | - | - | | 1.2049 | 530 | 0.13 | - | - | | 1.2276 | 540 | 0.1291 | - | - | | 1.2504 | 550 | 0.1287 | - | - | | 1.2732 | 560 | 0.1233 | - | - | | 1.2959 | 570 | 0.1242 | - | - | | 1.3187 | 580 | 0.1242 | - | - | | 1.3414 | 590 | 0.1227 | - | - | | 1.3642 | 600 | 0.1201 | - | - | | 1.3870 | 610 | 0.1247 | - | - | | 1.4097 | 620 | 0.1249 | - | - | | 1.4325 | 630 | 0.1213 | - | - | | 1.4553 | 640 | 0.1217 | - | - | | 1.4780 | 650 | 0.1204 | - | - | | 1.5008 | 660 | 0.1191 | - | - | | 1.5235 | 670 | 0.1163 | - | - | | 1.5463 | 680 | 0.1171 | - | - | | 1.5691 | 690 | 0.1208 | - | - | | 1.5918 | 700 | 0.1194 | - | - | | 1.6146 | 710 | 0.1173 | - | - | | 1.6374 | 720 | 0.1177 | - | - | | 1.6601 | 730 | 0.1148 | - | - | | 1.6829 | 740 | 0.1134 | - | - | | 1.7056 | 750 | 0.1167 | 0.0422 | 0.8092 | | 1.7284 | 760 | 0.1145 | - | - | | 1.7512 | 770 | 0.114 | - | - | | 1.7739 | 780 | 0.1136 | - | - | | 1.7967 | 790 | 0.1123 | - | - | | 1.8195 | 800 | 0.1115 | - | - | | 1.8422 | 810 | 0.1127 | - | - | | 1.8650 | 820 | 0.1137 | - | - | | 1.8878 | 830 | 0.1137 | - | - | | 1.9105 | 840 | 0.1123 | - | - | | 1.9333 | 850 | 0.1115 | - | - | | 1.9560 | 860 | 0.1105 | - | - | | 1.9788 | 870 | 0.1133 | - | - | | 2.0 | 880 | 0.1049 | - | - | | 2.0228 | 890 | 0.1091 | - | - | | 2.0455 | 900 | 0.111 | - | - | | 2.0683 | 910 | 0.1101 | - | - | | 2.0911 | 920 | 0.1078 | - | - | | 2.1138 | 930 | 0.1097 | - | - | | 2.1366 | 940 | 0.108 | - | - | | 2.1593 | 950 | 0.1077 | - | - | | 2.1821 | 960 | 0.1087 | - | - | | 2.2049 | 970 | 0.1058 | - | - | | 2.2276 | 980 | 0.1071 | - | - | | 2.2504 | 990 | 0.1058 | - | - | | 2.2732 | 1000 | 0.1104 | 0.0434 | 0.8156 | | 2.2959 | 1010 | 0.1036 | - | - | | 2.3187 | 1020 | 0.1068 | - | - | | 2.3414 | 1030 | 0.1033 | - | - | | 2.3642 | 1040 | 0.1058 | - | - | | 2.3870 | 1050 | 0.105 | - | - | | 2.4097 | 1060 | 0.1052 | - | - | | 2.4325 | 1070 | 0.1013 | - | - | | 2.4553 | 1080 | 0.1037 | - | - | | 2.4780 | 1090 | 0.1031 | - | - | | 2.5008 | 1100 | 0.1057 | - | - | | 2.5235 | 1110 | 0.1051 | - | - | | 2.5463 | 1120 | 0.1019 | - | - | | 2.5691 | 1130 | 0.1018 | - | - | | 2.5918 | 1140 | 0.1007 | - | - | | 2.6146 | 1150 | 0.1035 | - | - | | 2.6374 | 1160 | 0.1032 | - | - | | 2.6601 | 1170 | 0.1036 | - | - | | 2.6829 | 1180 | 0.0971 | - | - | | 2.7056 | 1190 | 0.1015 | - | - | | 2.7284 | 1200 | 0.104 | - | - | | 2.7512 | 1210 | 0.1007 | - | - | | 2.7739 | 1220 | 0.102 | - | - | | 2.7967 | 1230 | 0.0994 | - | - | | 2.8195 | 1240 | 0.0972 | - | - | | 2.8422 | 1250 | 0.0969 | 0.0437 | 0.8185 | | 2.8650 | 1260 | 0.0968 | - | - | | 2.8878 | 1270 | 0.1003 | - | - | | 2.9105 | 1280 | 0.1036 | - | - | | 2.9333 | 1290 | 0.0969 | - | - | | 2.9560 | 1300 | 0.0965 | - | - | | 2.9788 | 1310 | 0.0974 | - | - | | 3.0 | 1320 | 0.0905 | - | - | | 3.0228 | 1330 | 0.1006 | - | - | | 3.0455 | 1340 | 0.0952 | - | - | | 3.0683 | 1350 | 0.0971 | - | - | | 3.0911 | 1360 | 0.0943 | - | - | | 3.1138 | 1370 | 0.0996 | - | - | | 3.1366 | 1380 | 0.0971 | - | - | | 3.1593 | 1390 | 0.097 | - | - | | 3.1821 | 1400 | 0.0937 | - | - | | 3.2049 | 1410 | 0.0955 | - | - | | 3.2276 | 1420 | 0.0963 | - | - | | 3.2504 | 1430 | 0.0938 | - | - | | 3.2732 | 1440 | 0.0986 | - | - | | 3.2959 | 1450 | 0.0949 | - | - | | 3.3187 | 1460 | 0.0932 | - | - | | 3.3414 | 1470 | 0.096 | - | - | | 3.3642 | 1480 | 0.0919 | - | - | | 3.3870 | 1490 | 0.093 | - | - | | 3.4097 | 1500 | 0.0925 | 0.0438 | 0.8201 | | 3.4325 | 1510 | 0.0935 | - | - | | 3.4553 | 1520 | 0.0928 | - | - | | 3.4780 | 1530 | 0.0914 | - | - | | 3.5008 | 1540 | 0.0912 | - | - | | 3.5235 | 1550 | 0.091 | - | - | | 3.5463 | 1560 | 0.0906 | - | - | | 3.5691 | 1570 | 0.0936 | - | - | | 3.5918 | 1580 | 0.0943 | - | - | | 3.6146 | 1590 | 0.0925 | - | - | | 3.6374 | 1600 | 0.0908 | - | - | | 3.6601 | 1610 | 0.0933 | - | - | | 3.6829 | 1620 | 0.0917 | - | - | | 3.7056 | 1630 | 0.0887 | - | - | | 3.7284 | 1640 | 0.0903 | - | - | | 3.7512 | 1650 | 0.0934 | - | - | | 3.7739 | 1660 | 0.0906 | - | - | | 3.7967 | 1670 | 0.0886 | - | - | | 3.8195 | 1680 | 0.0915 | - | - | | 3.8422 | 1690 | 0.0924 | - | - | | 3.8650 | 1700 | 0.094 | - | - | | 3.8878 | 1710 | 0.0899 | - | - | | 3.9105 | 1720 | 0.0881 | - | - | | 3.9333 | 1730 | 0.0884 | - | - | | 3.9560 | 1740 | 0.0894 | - | - | | 3.9788 | 1750 | 0.0892 | 0.0441 | 0.8215 | | 4.0 | 1760 | 0.0812 | - | - | | 4.0228 | 1770 | 0.0878 | - | - | | 4.0455 | 1780 | 0.0869 | - | - | | 4.0683 | 1790 | 0.09 | - | - | | 4.0911 | 1800 | 0.0875 | - | - | | 4.1138 | 1810 | 0.086 | - | - | | 4.1366 | 1820 | 0.0888 | - | - | | 4.1593 | 1830 | 0.086 | - | - | | 4.1821 | 1840 | 0.0869 | - | - | | 4.2049 | 1850 | 0.0885 | - | - | | 4.2276 | 1860 | 0.0891 | - | - | | 4.2504 | 1870 | 0.0853 | - | - | | 4.2732 | 1880 | 0.0849 | - | - | | 4.2959 | 1890 | 0.0856 | - | - | | 4.3187 | 1900 | 0.0863 | - | - | | 4.3414 | 1910 | 0.0849 | - | - | | 4.3642 | 1920 | 0.0855 | - | - | | 4.3870 | 1930 | 0.0841 | - | - | | 4.4097 | 1940 | 0.0893 | - | - | | 4.4325 | 1950 | 0.0847 | - | - | | 4.4553 | 1960 | 0.0866 | - | - | | 4.4780 | 1970 | 0.0866 | - | - | | 4.5008 | 1980 | 0.0844 | - | - | | 4.5235 | 1990 | 0.0846 | - | - | | 4.5463 | 2000 | 0.0847 | 0.0435 | 0.8220 | | 4.5691 | 2010 | 0.0831 | - | - | | 4.5918 | 2020 | 0.0843 | - | - | | 4.6146 | 2030 | 0.086 | - | - | | 4.6374 | 2040 | 0.0851 | - | - | | 4.6601 | 2050 | 0.0844 | - | - | | 4.6829 | 2060 | 0.0843 | - | - | | 4.7056 | 2070 | 0.0854 | - | - | | 4.7284 | 2080 | 0.0851 | - | - | | 4.7512 | 2090 | 0.0822 | - | - | | 4.7739 | 2100 | 0.0859 | - | - | | 4.7967 | 2110 | 0.0844 | - | - | | 4.8195 | 2120 | 0.0853 | - | - | | 4.8422 | 2130 | 0.0815 | - | - | | 4.8650 | 2140 | 0.0833 | - | - | | 4.8878 | 2150 | 0.0817 | - | - | | 4.9105 | 2160 | 0.0873 | - | - | | 4.9333 | 2170 | 0.0813 | - | - | | 4.9560 | 2180 | 0.0829 | - | - | | 4.9788 | 2190 | 0.0812 | - | - | | 5.0 | 2200 | 0.0776 | - | - | | 5.0228 | 2210 | 0.083 | - | - | | 5.0455 | 2220 | 0.0821 | - | - | | 5.0683 | 2230 | 0.0806 | - | - | | 5.0911 | 2240 | 0.0809 | - | - | | 5.1138 | 2250 | 0.0814 | 0.0431 | 0.8225 | | 5.1366 | 2260 | 0.0808 | - | - | | 5.1593 | 2270 | 0.0791 | - | - | | 5.1821 | 2280 | 0.0811 | - | - | | 5.2049 | 2290 | 0.0805 | - | - | | 5.2276 | 2300 | 0.0817 | - | - | | 5.2504 | 2310 | 0.0772 | - | - | | 5.2732 | 2320 | 0.0799 | - | - | | 5.2959 | 2330 | 0.0829 | - | - | | 5.3187 | 2340 | 0.077 | - | - | | 5.3414 | 2350 | 0.0801 | - | - | | 5.3642 | 2360 | 0.0812 | - | - | | 5.3870 | 2370 | 0.0788 | - | - | | 5.4097 | 2380 | 0.0776 | - | - | | 5.4325 | 2390 | 0.0785 | - | - | | 5.4553 | 2400 | 0.0771 | - | - | | 5.4780 | 2410 | 0.0788 | - | - | | 5.5008 | 2420 | 0.0796 | - | - | | 5.5235 | 2430 | 0.0793 | - | - | | 5.5463 | 2440 | 0.0813 | - | - | | 5.5691 | 2450 | 0.0757 | - | - | | 5.5918 | 2460 | 0.079 | - | - | | 5.6146 | 2470 | 0.0797 | - | - | | 5.6374 | 2480 | 0.0794 | - | - | | 5.6601 | 2490 | 0.0808 | - | - | | 5.6829 | 2500 | 0.0796 | 0.0424 | 0.8230 | | 5.7056 | 2510 | 0.0802 | - | - | | 5.7284 | 2520 | 0.0799 | - | - | | 5.7512 | 2530 | 0.0802 | - | - | | 5.7739 | 2540 | 0.0813 | - | - | | 5.7967 | 2550 | 0.0772 | - | - | | 5.8195 | 2560 | 0.0766 | - | - | | 5.8422 | 2570 | 0.0778 | - | - | | 5.8650 | 2580 | 0.076 | - | - | | 5.8878 | 2590 | 0.0787 | - | - | | 5.9105 | 2600 | 0.0794 | - | - | | 5.9333 | 2610 | 0.076 | - | - | | 5.9560 | 2620 | 0.0773 | - | - | | 5.9788 | 2630 | 0.0755 | - | - | | 6.0 | 2640 | 0.0725 | - | - | | 6.0228 | 2650 | 0.0738 | - | - | | 6.0455 | 2660 | 0.0762 | - | - | | 6.0683 | 2670 | 0.0761 | - | - | | 6.0911 | 2680 | 0.0771 | - | - | | 6.1138 | 2690 | 0.0765 | - | - | | 6.1366 | 2700 | 0.0755 | - | - | | 6.1593 | 2710 | 0.0771 | - | - | | 6.1821 | 2720 | 0.0748 | - | - | | 6.2049 | 2730 | 0.0768 | - | - | | 6.2276 | 2740 | 0.0766 | - | - | | 6.2504 | 2750 | 0.0766 | 0.0422 | 0.8239 | | 6.2732 | 2760 | 0.076 | - | - | | 6.2959 | 2770 | 0.0753 | - | - | | 6.3187 | 2780 | 0.0735 | - | - | | 6.3414 | 2790 | 0.0751 | - | - | | 6.3642 | 2800 | 0.0738 | - | - | | 6.3870 | 2810 | 0.0749 | - | - | | 6.4097 | 2820 | 0.0753 | - | - | | 6.4325 | 2830 | 0.077 | - | - | | 6.4553 | 2840 | 0.0747 | - | - | | 6.4780 | 2850 | 0.0722 | - | - | | 6.5008 | 2860 | 0.0736 | - | - | | 6.5235 | 2870 | 0.073 | - | - | | 6.5463 | 2880 | 0.0774 | - | - | | 6.5691 | 2890 | 0.075 | - | - | | 6.5918 | 2900 | 0.0718 | - | - | | 6.6146 | 2910 | 0.0727 | - | - | | 6.6374 | 2920 | 0.0735 | - | - | | 6.6601 | 2930 | 0.0726 | - | - | | 6.6829 | 2940 | 0.075 | - | - | | 6.7056 | 2950 | 0.0728 | - | - | | 6.7284 | 2960 | 0.0713 | - | - | | 6.7512 | 2970 | 0.0722 | - | - | | 6.7739 | 2980 | 0.0753 | - | - | | 6.7967 | 2990 | 0.0733 | - | - | | 6.8195 | 3000 | 0.0727 | 0.0425 | 0.8243 | | 6.8422 | 3010 | 0.0729 | - | - | | 6.8650 | 3020 | 0.073 | - | - | | 6.8878 | 3030 | 0.0739 | - | - | | 6.9105 | 3040 | 0.0717 | - | - | | 6.9333 | 3050 | 0.0719 | - | - | | 6.9560 | 3060 | 0.0712 | - | - | | 6.9788 | 3070 | 0.0712 | - | - | | 7.0 | 3080 | 0.0674 | - | - | | 7.0228 | 3090 | 0.0729 | - | - | | 7.0455 | 3100 | 0.0712 | - | - | | 7.0683 | 3110 | 0.0701 | - | - | | 7.0911 | 3120 | 0.0699 | - | - | | 7.1138 | 3130 | 0.0675 | - | - | | 7.1366 | 3140 | 0.0699 | - | - | | 7.1593 | 3150 | 0.0716 | - | - | | 7.1821 | 3160 | 0.0707 | - | - | | 7.2049 | 3170 | 0.0717 | - | - | | 7.2276 | 3180 | 0.0709 | - | - | | 7.2504 | 3190 | 0.071 | - | - | | 7.2732 | 3200 | 0.0722 | - | - | | 7.2959 | 3210 | 0.072 | - | - | | 7.3187 | 3220 | 0.0729 | - | - | | 7.3414 | 3230 | 0.0678 | - | - | | 7.3642 | 3240 | 0.0705 | - | - | | 7.3870 | 3250 | 0.0715 | 0.0426 | 0.8256 | | 7.4097 | 3260 | 0.0703 | - | - | | 7.4325 | 3270 | 0.0699 | - | - | | 7.4553 | 3280 | 0.071 | - | - | | 7.4780 | 3290 | 0.0692 | - | - | | 7.5008 | 3300 | 0.0693 | - | - | | 7.5235 | 3310 | 0.0661 | - | - | | 7.5463 | 3320 | 0.0702 | - | - | | 7.5691 | 3330 | 0.0697 | - | - | | 7.5918 | 3340 | 0.072 | - | - | | 7.6146 | 3350 | 0.0693 | - | - | | 7.6374 | 3360 | 0.0691 | - | - | | 7.6601 | 3370 | 0.0702 | - | - | | 7.6829 | 3380 | 0.0672 | - | - | | 7.7056 | 3390 | 0.0698 | - | - | | 7.7284 | 3400 | 0.0687 | - | - | | 7.7512 | 3410 | 0.0654 | - | - | | 7.7739 | 3420 | 0.0687 | - | - | | 7.7967 | 3430 | 0.0679 | - | - | | 7.8195 | 3440 | 0.0713 | - | - | | 7.8422 | 3450 | 0.0676 | - | - | | 7.8650 | 3460 | 0.0708 | - | - | | 7.8878 | 3470 | 0.0666 | - | - | | 7.9105 | 3480 | 0.0675 | - | - | | 7.9333 | 3490 | 0.0693 | - | - | | 7.9560 | 3500 | 0.0688 | 0.0427 | 0.8260 | | 7.9788 | 3510 | 0.068 | - | - | | 8.0 | 3520 | 0.063 | - | - | | 8.0228 | 3530 | 0.0659 | - | - | | 8.0455 | 3540 | 0.0639 | - | - | | 8.0683 | 3550 | 0.0678 | - | - | | 8.0911 | 3560 | 0.0689 | - | - | | 8.1138 | 3570 | 0.0687 | - | - | | 8.1366 | 3580 | 0.0672 | - | - | | 8.1593 | 3590 | 0.0659 | - | - | | 8.1821 | 3600 | 0.0658 | - | - | | 8.2049 | 3610 | 0.0664 | - | - | | 8.2276 | 3620 | 0.0659 | - | - | | 8.2504 | 3630 | 0.0664 | - | - | | 8.2732 | 3640 | 0.0652 | - | - | | 8.2959 | 3650 | 0.0683 | - | - | | 8.3187 | 3660 | 0.0641 | - | - | | 8.3414 | 3670 | 0.0672 | - | - | | 8.3642 | 3680 | 0.0655 | - | - | | 8.3870 | 3690 | 0.0661 | - | - | | 8.4097 | 3700 | 0.0638 | - | - | | 8.4325 | 3710 | 0.0675 | - | - | | 8.4553 | 3720 | 0.0648 | - | - | | 8.4780 | 3730 | 0.067 | - | - | | 8.5008 | 3740 | 0.0684 | - | - | | 8.5235 | 3750 | 0.0667 | 0.0420 | 0.8268 | | 8.5463 | 3760 | 0.0645 | - | - | | 8.5691 | 3770 | 0.0652 | - | - | | 8.5918 | 3780 | 0.0633 | - | - | | 8.6146 | 3790 | 0.065 | - | - | | 8.6374 | 3800 | 0.064 | - | - | | 8.6601 | 3810 | 0.0677 | - | - | | 8.6829 | 3820 | 0.0661 | - | - | | 8.7056 | 3830 | 0.0653 | - | - | | 8.7284 | 3840 | 0.0625 | - | - | | 8.7512 | 3850 | 0.0651 | - | - | | 8.7739 | 3860 | 0.0656 | - | - | | 8.7967 | 3870 | 0.0636 | - | - | | 8.8195 | 3880 | 0.0655 | - | - | | 8.8422 | 3890 | 0.0647 | - | - | | 8.8650 | 3900 | 0.0638 | - | - | | 8.8878 | 3910 | 0.0636 | - | - | | 8.9105 | 3920 | 0.0666 | - | - | | 8.9333 | 3930 | 0.062 | - | - | | 8.9560 | 3940 | 0.065 | - | - | | 8.9788 | 3950 | 0.0643 | - | - | | 9.0 | 3960 | 0.0594 | - | - | | 9.0228 | 3970 | 0.0616 | - | - | | 9.0455 | 3980 | 0.0638 | - | - | | 9.0683 | 3990 | 0.0625 | - | - | | 9.0911 | 4000 | 0.0665 | 0.0414 | 0.8276 | | 9.1138 | 4010 | 0.0624 | - | - | | 9.1366 | 4020 | 0.0621 | - | - | | 9.1593 | 4030 | 0.0648 | - | - | | 9.1821 | 4040 | 0.0622 | - | - | | 9.2049 | 4050 | 0.0635 | - | - | | 9.2276 | 4060 | 0.061 | - | - | | 9.2504 | 4070 | 0.0602 | - | - | | 9.2732 | 4080 | 0.0613 | - | - | | 9.2959 | 4090 | 0.0604 | - | - | | 9.3187 | 4100 | 0.0623 | - | - | | 9.3414 | 4110 | 0.0641 | - | - | | 9.3642 | 4120 | 0.0635 | - | - | | 9.3870 | 4130 | 0.0608 | - | - | | 9.4097 | 4140 | 0.0611 | - | - | | 9.4325 | 4150 | 0.0607 | - | - | | 9.4553 | 4160 | 0.0631 | - | - | | 9.4780 | 4170 | 0.0618 | - | - | | 9.5008 | 4180 | 0.0609 | - | - | | 9.5235 | 4190 | 0.0613 | - | - | | 9.5463 | 4200 | 0.0606 | - | - | | 9.5691 | 4210 | 0.0595 | - | - | | 9.5918 | 4220 | 0.0609 | - | - | | 9.6146 | 4230 | 0.061 | - | - | | 9.6374 | 4240 | 0.0616 | - | - | | 9.6601 | 4250 | 0.0613 | 0.0418 | 0.8282 | | 9.6829 | 4260 | 0.0623 | - | - | | 9.7056 | 4270 | 0.0605 | - | - | | 9.7284 | 4280 | 0.0637 | - | - | | 9.7512 | 4290 | 0.0604 | - | - | | 9.7739 | 4300 | 0.0606 | - | - | | 9.7967 | 4310 | 0.0622 | - | - | | 9.8195 | 4320 | 0.0598 | - | - | | 9.8422 | 4330 | 0.0611 | - | - | | 9.8650 | 4340 | 0.0604 | - | - | | 9.8878 | 4350 | 0.0598 | - | - | | 9.9105 | 4360 | 0.0626 | - | - | | 9.9333 | 4370 | 0.0624 | - | - | | 9.9560 | 4380 | 0.0617 | - | - | | 9.9788 | 4390 | 0.0603 | - | - |
### Framework Versions - Python: 3.11.10 - Sentence Transformers: 3.4.1 - Transformers: 4.48.3 - PyTorch: 2.5.1+cu124 - Accelerate: 1.3.0 - Datasets: 3.3.0 - Tokenizers: 0.21.0 ## 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", } ```