--- base_model: nomic-ai/nomic-embed-text-v1.5 datasets: [] language: [] library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:756057 - loss:MultipleNegativesRankingLoss widget: - source_sentence: 府君奈何以蓋世之才欲立忠於垂亡之國 sentences: - 將遠方進貢來的奇獸飛禽以及白山雞等物縱還山林比起雍畤的祭祀禮數頗有增加 - 您為什麼以蓋絕當世的奇才卻打算向這個面臨滅亡的國家盡效忠心呢 - 大統年間他出任岐州刺史在任不久就因為能力強而聞名 - source_sentence: 將率既至授單于印紱詔令上故印紱 sentences: - 已經到達的五威將到達後授給單于新印信宣讀詔書要求交回漢朝舊印信 - 於是拜陶隗為西南面招討使 - 司馬錯建議秦惠王攻打蜀國張儀說 還不如進攻韓國 - source_sentence: 行醮禮皇太子詣醴席樂作 sentences: - 閏七月十七日上宣宗廢除皇后胡氏尊諡 - 等到看見西羌鼠竊狗盜父不父子不子君臣沒有分別四夷之人西羌最為低下 - 行醮禮皇太子來到酒醴席奏樂 - source_sentence: 領軍臧盾太府卿沈僧果等並被時遇孝綽尤輕之 sentences: - 過了幾天太宰官又來要國書並且說 我國自太宰府以東上國使臣沒有到過今大朝派使臣來若不見國書何以相信 - 所以丹陽葛洪解釋說渾天儀注說 天體像雞蛋地就像是雞蛋中的蛋黃獨處於天體之內天是大的而地是小的 - 領軍臧盾太府卿沈僧果等都是因趕上時機而得到官職的孝綽尤其輕蔑他們每次在朝中集合會面雖然一起做官但從不與他們說話 - source_sentence: 九月辛未太祖曾孫舒國公從式進封安定郡王 sentences: - 九月初二太祖曾孫舒國公從式進封安定郡王 - 楊難當在漢中大肆燒殺搶劫然後率眾離開了漢中向西返回仇池留下趙溫據守梁州又派他的魏興太守薛健屯駐黃金山 - 正統元年普定蠻夷阿遲等反叛非法稱王四處出擊攻打掠奪 --- # SentenceTransformer based on nomic-ai/nomic-embed-text-v1.5 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [nomic-ai/nomic-embed-text-v1.5](https://huggingface.co./nomic-ai/nomic-embed-text-v1.5). 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:** [nomic-ai/nomic-embed-text-v1.5](https://huggingface.co./nomic-ai/nomic-embed-text-v1.5) - **Maximum Sequence Length:** 8192 tokens - **Output Dimensionality:** 768 tokens - **Similarity Function:** Cosine Similarity ### 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': 8192, 'do_lower_case': False}) with Transformer model: NomicBertModel (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("sentence_transformers_model_id") # Run inference sentences = [ '九月辛未太祖曾孫舒國公從式進封安定郡王', '九月初二太祖曾孫舒國公從式進封安定郡王', '楊難當在漢中大肆燒殺搶劫然後率眾離開了漢中向西返回仇池留下趙溫據守梁州又派他的魏興太守薛健屯駐黃金山', ] 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] ``` ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 756,057 training samples * Columns: anchor and positive * Approximate statistics based on the first 1000 samples: | | anchor | positive | |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | anchor | positive | |:------------------------------------------|:------------------------------------------------------------| | 虜懷兼弱之威挾廣地之計強兵大眾親自凌殄旍鼓彌年矢石不息 | 魏人懷有兼併弱小的威嚴胸藏拓展土地的計謀強人的軍隊親自出徵侵逼消滅旌旗戰鼓連年出動戰事不停息 | | 孟子曰 以善服人者未有能服人者也以善養人然後能服天下 | 孟子說 用自己的善良使人們服從的人沒有能使人服從的用善良影響教導人們才能使天下的人們都信服 | | 開慶初大元兵渡江理宗議遷都平江慶元后諫不可恐搖動民心乃止 | 開慶初年大元朝部隊渡過長江理宗打算遷都到平江慶元皇后勸諫不可遷都深恐動搖民心理宗才作罷 | * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Evaluation Dataset #### Unnamed Dataset * Size: 84,007 evaluation samples * Columns: anchor and positive * Approximate statistics based on the first 1000 samples: | | anchor | positive | |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | anchor | positive | |:--------------------------------------------------|:------------------------------------------------------------------| | 雒陽戶五萬二千八百三十九 | 雒陽有五萬二千八百三十九戶 | | 拜南青州刺史在任有政績 | 任南青州刺史很有政績 | | 第六品以下加不得服金釒奠綾錦錦繡七緣綺貂豽裘金叉環鉺及以金校飾器物張絳帳 | 官位在第六品以下的官員再增加不得穿用金鈿綾錦錦繡七緣綺貂鈉皮衣金叉繯餌以及用金裝飾的器物張絳帳等衣服物品 | * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `num_train_epochs`: 1 - `warmup_ratio`: 0.1 - `fp16`: True - `load_best_model_at_end`: 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`: 16 - `per_device_eval_batch_size`: 16 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `eval_accumulation_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`: 1 - `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`: True - `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`: False - `resume_from_checkpoint`: None - `hub_model_id`: None - `hub_strategy`: every_save - `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 | |:----------:|:---------:|:-------------:|:----------:| | 0.0021 | 100 | 0.4574 | - | | 0.0042 | 200 | 0.4089 | - | | 0.0063 | 300 | 0.2872 | - | | 0.0085 | 400 | 0.2909 | - | | 0.0106 | 500 | 0.3076 | - | | 0.0127 | 600 | 0.2958 | - | | 0.0148 | 700 | 0.2953 | - | | 0.0169 | 800 | 0.31 | - | | 0.0190 | 900 | 0.3031 | - | | 0.0212 | 1000 | 0.263 | - | | 0.0233 | 1100 | 0.27 | - | | 0.0254 | 1200 | 0.3107 | - | | 0.0275 | 1300 | 0.2453 | - | | 0.0296 | 1400 | 0.2487 | - | | 0.0317 | 1500 | 0.2332 | - | | 0.0339 | 1600 | 0.2708 | - | | 0.0360 | 1700 | 0.2731 | - | | 0.0381 | 1800 | 0.3102 | - | | 0.0402 | 1900 | 0.3385 | - | | 0.0423 | 2000 | 0.2802 | - | | 0.0444 | 2100 | 0.3348 | - | | 0.0466 | 2200 | 0.2527 | - | | 0.0487 | 2300 | 0.2916 | - | | 0.0508 | 2400 | 0.2671 | - | | 0.0529 | 2500 | 0.2187 | - | | 0.0550 | 2600 | 0.2624 | - | | 0.0571 | 2700 | 0.3061 | - | | 0.0593 | 2800 | 0.2439 | - | | 0.0614 | 2900 | 0.2831 | - | | 0.0635 | 3000 | 0.2948 | - | | 0.0656 | 3100 | 0.2828 | - | | 0.0677 | 3200 | 0.3079 | - | | 0.0698 | 3300 | 0.3194 | - | | 0.0720 | 3400 | 0.2768 | - | | 0.0741 | 3500 | 0.304 | - | | 0.0762 | 3600 | 0.3056 | - | | 0.0783 | 3700 | 0.2562 | - | | 0.0804 | 3800 | 0.3138 | - | | 0.0825 | 3900 | 0.3081 | - | | 0.0846 | 4000 | 0.2733 | - | | 0.0868 | 4100 | 0.3065 | - | | 0.0889 | 4200 | 0.25 | - | | 0.0910 | 4300 | 0.3076 | - | | 0.0931 | 4400 | 0.2935 | - | | 0.0952 | 4500 | 0.2644 | - | | 0.0973 | 4600 | 0.2943 | - | | 0.0995 | 4700 | 0.316 | - | | 0.1016 | 4800 | 0.2616 | - | | 0.1037 | 4900 | 0.2985 | - | | 0.1058 | 5000 | 0.2962 | 0.2798 | | 0.1079 | 5100 | 0.2872 | - | | 0.1100 | 5200 | 0.2963 | - | | 0.1122 | 5300 | 0.2968 | - | | 0.1143 | 5400 | 0.2738 | - | | 0.1164 | 5500 | 0.3198 | - | | 0.1185 | 5600 | 0.294 | - | | 0.1206 | 5700 | 0.3296 | - | | 0.1227 | 5800 | 0.2605 | - | | 0.1249 | 5900 | 0.3187 | - | | 0.1270 | 6000 | 0.2657 | - | | 0.1291 | 6100 | 0.3267 | - | | 0.1312 | 6200 | 0.3839 | - | | 0.1333 | 6300 | 0.3077 | - | | 0.1354 | 6400 | 0.205 | - | | 0.1376 | 6500 | 0.2839 | - | | 0.1397 | 6600 | 0.3037 | - | | 0.1418 | 6700 | 0.2694 | - | | 0.1439 | 6800 | 0.2956 | - | | 0.1460 | 6900 | 0.261 | - | | 0.1481 | 7000 | 0.3173 | - | | 0.1503 | 7100 | 0.2492 | - | | 0.1524 | 7200 | 0.2885 | - | | 0.1545 | 7300 | 0.3059 | - | | 0.1566 | 7400 | 0.2883 | - | | 0.1587 | 7500 | 0.2465 | - | | 0.1608 | 7600 | 0.2926 | - | | 0.1629 | 7700 | 0.2776 | - | | 0.1651 | 7800 | 0.2769 | - | | 0.1672 | 7900 | 0.2644 | - | | 0.1693 | 8000 | 0.2416 | - | | 0.1714 | 8100 | 0.254 | - | | 0.1735 | 8200 | 0.2485 | - | | 0.1756 | 8300 | 0.3029 | - | | 0.1778 | 8400 | 0.2938 | - | | 0.1799 | 8500 | 0.2936 | - | | 0.1820 | 8600 | 0.2804 | - | | 0.1841 | 8700 | 0.2408 | - | | 0.1862 | 8800 | 0.2849 | - | | 0.1883 | 8900 | 0.2954 | - | | 0.1905 | 9000 | 0.2902 | - | | 0.1926 | 9100 | 0.2845 | - | | 0.1947 | 9200 | 0.3143 | - | | 0.1968 | 9300 | 0.2514 | - | | 0.1989 | 9400 | 0.2508 | - | | 0.2010 | 9500 | 0.2782 | - | | 0.2032 | 9600 | 0.291 | - | | 0.2053 | 9700 | 0.2464 | - | | 0.2074 | 9800 | 0.323 | - | | 0.2095 | 9900 | 0.2332 | - | | 0.2116 | 10000 | 0.2231 | 0.2521 | | 0.2137 | 10100 | 0.245 | - | | 0.2159 | 10200 | 0.2883 | - | | 0.2180 | 10300 | 0.3097 | - | | 0.2201 | 10400 | 0.2303 | - | | 0.2222 | 10500 | 0.3194 | - | | 0.2243 | 10600 | 0.2836 | - | | 0.2264 | 10700 | 0.2727 | - | | 0.2286 | 10800 | 0.2542 | - | | 0.2307 | 10900 | 0.2708 | - | | 0.2328 | 11000 | 0.263 | - | | 0.2349 | 11100 | 0.3063 | - | | 0.2370 | 11200 | 0.2667 | - | | 0.2391 | 11300 | 0.2575 | - | | 0.2412 | 11400 | 0.2487 | - | | 0.2434 | 11500 | 0.2552 | - | | 0.2455 | 11600 | 0.2669 | - | | 0.2476 | 11700 | 0.2241 | - | | 0.2497 | 11800 | 0.3029 | - | | 0.2518 | 11900 | 0.2443 | - | | 0.2539 | 12000 | 0.2961 | - | | 0.2561 | 12100 | 0.2561 | - | | 0.2582 | 12200 | 0.2436 | - | | 0.2603 | 12300 | 0.2601 | - | | 0.2624 | 12400 | 0.2553 | - | | 0.2645 | 12500 | 0.2617 | - | | 0.2666 | 12600 | 0.2581 | - | | 0.2688 | 12700 | 0.2452 | - | | 0.2709 | 12800 | 0.2227 | - | | 0.2730 | 12900 | 0.2455 | - | | 0.2751 | 13000 | 0.2469 | - | | 0.2772 | 13100 | 0.2197 | - | | 0.2793 | 13200 | 0.3086 | - | | 0.2815 | 13300 | 0.2379 | - | | 0.2836 | 13400 | 0.2441 | - | | 0.2857 | 13500 | 0.2854 | - | | 0.2878 | 13600 | 0.2405 | - | | 0.2899 | 13700 | 0.2681 | - | | 0.2920 | 13800 | 0.2405 | - | | 0.2942 | 13900 | 0.251 | - | | 0.2963 | 14000 | 0.2477 | - | | 0.2984 | 14100 | 0.231 | - | | 0.3005 | 14200 | 0.26 | - | | 0.3026 | 14300 | 0.2395 | - | | 0.3047 | 14400 | 0.2296 | - | | 0.3069 | 14500 | 0.2554 | - | | 0.3090 | 14600 | 0.2434 | - | | 0.3111 | 14700 | 0.2247 | - | | 0.3132 | 14800 | 0.267 | - | | 0.3153 | 14900 | 0.2212 | - | | 0.3174 | 15000 | 0.2744 | 0.2352 | | 0.3195 | 15100 | 0.2168 | - | | 0.3217 | 15200 | 0.2042 | - | | 0.3238 | 15300 | 0.2187 | - | | 0.3259 | 15400 | 0.2368 | - | | 0.3280 | 15500 | 0.2693 | - | | 0.3301 | 15600 | 0.255 | - | | 0.3322 | 15700 | 0.2398 | - | | 0.3344 | 15800 | 0.247 | - | | 0.3365 | 15900 | 0.2431 | - | | 0.3386 | 16000 | 0.2349 | - | | 0.3407 | 16100 | 0.212 | - | | 0.3428 | 16200 | 0.2875 | - | | 0.3449 | 16300 | 0.2571 | - | | 0.3471 | 16400 | 0.2513 | - | | 0.3492 | 16500 | 0.2729 | - | | 0.3513 | 16600 | 0.2755 | - | | 0.3534 | 16700 | 0.2079 | - | | 0.3555 | 16800 | 0.1997 | - | | 0.3576 | 16900 | 0.2217 | - | | 0.3598 | 17000 | 0.1887 | - | | 0.3619 | 17100 | 0.2623 | - | | 0.3640 | 17200 | 0.2049 | - | | 0.3661 | 17300 | 0.2 | - | | 0.3682 | 17400 | 0.2367 | - | | 0.3703 | 17500 | 0.2368 | - | | 0.3725 | 17600 | 0.2311 | - | | 0.3746 | 17700 | 0.2359 | - | | 0.3767 | 17800 | 0.2586 | - | | 0.3788 | 17900 | 0.2222 | - | | 0.3809 | 18000 | 0.2561 | - | | 0.3830 | 18100 | 0.2246 | - | | 0.3852 | 18200 | 0.1871 | - | | 0.3873 | 18300 | 0.2147 | - | | 0.3894 | 18400 | 0.2741 | - | | 0.3915 | 18500 | 0.2079 | - | | 0.3936 | 18600 | 0.2399 | - | | 0.3957 | 18700 | 0.2375 | - | | 0.3978 | 18800 | 0.2502 | - | | 0.4000 | 18900 | 0.2385 | - | | 0.4021 | 19000 | 0.2647 | - | | 0.4042 | 19100 | 0.1847 | - | | 0.4063 | 19200 | 0.2367 | - | | 0.4084 | 19300 | 0.2148 | - | | 0.4105 | 19400 | 0.1826 | - | | 0.4127 | 19500 | 0.225 | - | | 0.4148 | 19600 | 0.2415 | - | | 0.4169 | 19700 | 0.2998 | - | | 0.4190 | 19800 | 0.2435 | - | | 0.4211 | 19900 | 0.2283 | - | | 0.4232 | 20000 | 0.2782 | 0.2263 | | 0.4254 | 20100 | 0.2786 | - | | 0.4275 | 20200 | 0.2695 | - | | 0.4296 | 20300 | 0.2112 | - | | 0.4317 | 20400 | 0.2006 | - | | 0.4338 | 20500 | 0.2031 | - | | 0.4359 | 20600 | 0.2335 | - | | 0.4381 | 20700 | 0.2154 | - | | 0.4402 | 20800 | 0.2225 | - | | 0.4423 | 20900 | 0.2234 | - | | 0.4444 | 21000 | 0.2233 | - | | 0.4465 | 21100 | 0.1851 | - | | 0.4486 | 21200 | 0.2009 | - | | 0.4508 | 21300 | 0.2337 | - | | 0.4529 | 21400 | 0.2175 | - | | 0.4550 | 21500 | 0.2564 | - | | 0.4571 | 21600 | 0.205 | - | | 0.4592 | 21700 | 0.233 | - | | 0.4613 | 21800 | 0.2027 | - | | 0.4635 | 21900 | 0.209 | - | | 0.4656 | 22000 | 0.261 | - | | 0.4677 | 22100 | 0.1755 | - | | 0.4698 | 22200 | 0.2219 | - | | 0.4719 | 22300 | 0.2108 | - | | 0.4740 | 22400 | 0.212 | - | | 0.4762 | 22500 | 0.2676 | - | | 0.4783 | 22600 | 0.2314 | - | | 0.4804 | 22700 | 0.1838 | - | | 0.4825 | 22800 | 0.1967 | - | | 0.4846 | 22900 | 0.2412 | - | | 0.4867 | 23000 | 0.2203 | - | | 0.4888 | 23100 | 0.2183 | - | | 0.4910 | 23200 | 0.239 | - | | 0.4931 | 23300 | 0.2273 | - | | 0.4952 | 23400 | 0.2335 | - | | 0.4973 | 23500 | 0.202 | - | | 0.4994 | 23600 | 0.2176 | - | | 0.5015 | 23700 | 0.2331 | - | | 0.5037 | 23800 | 0.1949 | - | | 0.5058 | 23900 | 0.2321 | - | | 0.5079 | 24000 | 0.2046 | - | | 0.5100 | 24100 | 0.2092 | - | | 0.5121 | 24200 | 0.2195 | - | | 0.5142 | 24300 | 0.2069 | - | | 0.5164 | 24400 | 0.2049 | - | | 0.5185 | 24500 | 0.2955 | - | | 0.5206 | 24600 | 0.2101 | - | | 0.5227 | 24700 | 0.2036 | - | | 0.5248 | 24800 | 0.2507 | - | | 0.5269 | 24900 | 0.2343 | - | | 0.5291 | 25000 | 0.2026 | 0.2072 | | 0.5312 | 25100 | 0.2288 | - | | 0.5333 | 25200 | 0.2208 | - | | 0.5354 | 25300 | 0.1914 | - | | 0.5375 | 25400 | 0.1903 | - | | 0.5396 | 25500 | 0.2156 | - | | 0.5418 | 25600 | 0.216 | - | | 0.5439 | 25700 | 0.1909 | - | | 0.5460 | 25800 | 0.2265 | - | | 0.5481 | 25900 | 0.2447 | - | | 0.5502 | 26000 | 0.1879 | - | | 0.5523 | 26100 | 0.204 | - | | 0.5545 | 26200 | 0.2262 | - | | 0.5566 | 26300 | 0.2448 | - | | 0.5587 | 26400 | 0.1758 | - | | 0.5608 | 26500 | 0.2102 | - | | 0.5629 | 26600 | 0.2175 | - | | 0.5650 | 26700 | 0.2109 | - | | 0.5671 | 26800 | 0.202 | - | | 0.5693 | 26900 | 0.2075 | - | | 0.5714 | 27000 | 0.2021 | - | | 0.5735 | 27100 | 0.1799 | - | | 0.5756 | 27200 | 0.2084 | - | | 0.5777 | 27300 | 0.2114 | - | | 0.5798 | 27400 | 0.1851 | - | | 0.5820 | 27500 | 0.22 | - | | 0.5841 | 27600 | 0.181 | - | | 0.5862 | 27700 | 0.2276 | - | | 0.5883 | 27800 | 0.1944 | - | | 0.5904 | 27900 | 0.1907 | - | | 0.5925 | 28000 | 0.2176 | - | | 0.5947 | 28100 | 0.2243 | - | | 0.5968 | 28200 | 0.2191 | - | | 0.5989 | 28300 | 0.2215 | - | | 0.6010 | 28400 | 0.1769 | - | | 0.6031 | 28500 | 0.1971 | - | | 0.6052 | 28600 | 0.179 | - | | 0.6074 | 28700 | 0.2308 | - | | 0.6095 | 28800 | 0.2453 | - | | 0.6116 | 28900 | 0.2293 | - | | 0.6137 | 29000 | 0.2191 | - | | 0.6158 | 29100 | 0.1988 | - | | 0.6179 | 29200 | 0.1878 | - | | 0.6201 | 29300 | 0.2215 | - | | 0.6222 | 29400 | 0.2188 | - | | 0.6243 | 29500 | 0.1821 | - | | 0.6264 | 29600 | 0.1856 | - | | 0.6285 | 29700 | 0.1907 | - | | 0.6306 | 29800 | 0.1999 | - | | 0.6328 | 29900 | 0.1803 | - | | 0.6349 | 30000 | 0.201 | 0.1948 | | 0.6370 | 30100 | 0.179 | - | | 0.6391 | 30200 | 0.2073 | - | | 0.6412 | 30300 | 0.2676 | - | | 0.6433 | 30400 | 0.1824 | - | | 0.6454 | 30500 | 0.1995 | - | | 0.6476 | 30600 | 0.2097 | - | | 0.6497 | 30700 | 0.2421 | - | | 0.6518 | 30800 | 0.1745 | - | | 0.6539 | 30900 | 0.2682 | - | | 0.6560 | 31000 | 0.1892 | - | | 0.6581 | 31100 | 0.2054 | - | | 0.6603 | 31200 | 0.23 | - | | 0.6624 | 31300 | 0.1711 | - | | 0.6645 | 31400 | 0.2163 | - | | 0.6666 | 31500 | 0.196 | - | | 0.6687 | 31600 | 0.1746 | - | | 0.6708 | 31700 | 0.2402 | - | | 0.6730 | 31800 | 0.2096 | - | | 0.6751 | 31900 | 0.1934 | - | | 0.6772 | 32000 | 0.2021 | - | | 0.6793 | 32100 | 0.1942 | - | | 0.6814 | 32200 | 0.2076 | - | | 0.6835 | 32300 | 0.1662 | - | | 0.6857 | 32400 | 0.1777 | - | | 0.6878 | 32500 | 0.1899 | - | | 0.6899 | 32600 | 0.2253 | - | | 0.6920 | 32700 | 0.221 | - | | 0.6941 | 32800 | 0.1797 | - | | 0.6962 | 32900 | 0.1884 | - | | 0.6984 | 33000 | 0.2185 | - | | 0.7005 | 33100 | 0.193 | - | | 0.7026 | 33200 | 0.1975 | - | | 0.7047 | 33300 | 0.1774 | - | | 0.7068 | 33400 | 0.1709 | - | | 0.7089 | 33500 | 0.1753 | - | | 0.7111 | 33600 | 0.1834 | - | | 0.7132 | 33700 | 0.1853 | - | | 0.7153 | 33800 | 0.2155 | - | | 0.7174 | 33900 | 0.1837 | - | | 0.7195 | 34000 | 0.1655 | - | | 0.7216 | 34100 | 0.212 | - | | 0.7237 | 34200 | 0.2203 | - | | 0.7259 | 34300 | 0.2267 | - | | 0.7280 | 34400 | 0.208 | - | | 0.7301 | 34500 | 0.1545 | - | | 0.7322 | 34600 | 0.2003 | - | | 0.7343 | 34700 | 0.2058 | - | | 0.7364 | 34800 | 0.1837 | - | | 0.7386 | 34900 | 0.2199 | - | | 0.7407 | 35000 | 0.1931 | 0.1848 | | 0.7428 | 35100 | 0.2456 | - | | 0.7449 | 35200 | 0.1996 | - | | 0.7470 | 35300 | 0.2145 | - | | 0.7491 | 35400 | 0.1915 | - | | 0.7513 | 35500 | 0.1734 | - | | 0.7534 | 35600 | 0.19 | - | | 0.7555 | 35700 | 0.182 | - | | 0.7576 | 35800 | 0.1808 | - | | 0.7597 | 35900 | 0.1625 | - | | 0.7618 | 36000 | 0.1813 | - | | 0.7640 | 36100 | 0.1412 | - | | 0.7661 | 36200 | 0.2279 | - | | 0.7682 | 36300 | 0.2444 | - | | 0.7703 | 36400 | 0.1882 | - | | 0.7724 | 36500 | 0.1731 | - | | 0.7745 | 36600 | 0.1794 | - | | 0.7767 | 36700 | 0.2577 | - | | 0.7788 | 36800 | 0.169 | - | | 0.7809 | 36900 | 0.1725 | - | | 0.7830 | 37000 | 0.1788 | - | | 0.7851 | 37100 | 0.1783 | - | | 0.7872 | 37200 | 0.1764 | - | | 0.7894 | 37300 | 0.1616 | - | | 0.7915 | 37400 | 0.21 | - | | 0.7936 | 37500 | 0.2091 | - | | 0.7957 | 37600 | 0.1107 | - | | 0.7978 | 37700 | 0.1773 | - | | 0.7999 | 37800 | 0.1801 | - | | 0.8020 | 37900 | 0.1621 | - | | 0.8042 | 38000 | 0.189 | - | | 0.8063 | 38100 | 0.182 | - | | 0.8084 | 38200 | 0.1912 | - | | 0.8105 | 38300 | 0.1731 | - | | 0.8126 | 38400 | 0.1646 | - | | 0.8147 | 38500 | 0.2037 | - | | 0.8169 | 38600 | 0.1418 | - | | 0.8190 | 38700 | 0.1485 | - | | 0.8211 | 38800 | 0.2221 | - | | 0.8232 | 38900 | 0.1886 | - | | 0.8253 | 39000 | 0.2082 | - | | 0.8274 | 39100 | 0.1742 | - | | 0.8296 | 39200 | 0.1589 | - | | 0.8317 | 39300 | 0.1959 | - | | 0.8338 | 39400 | 0.1517 | - | | 0.8359 | 39500 | 0.2049 | - | | 0.8380 | 39600 | 0.2187 | - | | 0.8401 | 39700 | 0.1801 | - | | 0.8423 | 39800 | 0.1735 | - | | 0.8444 | 39900 | 0.1881 | - | | 0.8465 | 40000 | 0.1778 | 0.1787 | | 0.8486 | 40100 | 0.1898 | - | | 0.8507 | 40200 | 0.2021 | - | | 0.8528 | 40300 | 0.1972 | - | | 0.8550 | 40400 | 0.156 | - | | 0.8571 | 40500 | 0.1791 | - | | 0.8592 | 40600 | 0.188 | - | | 0.8613 | 40700 | 0.2177 | - | | 0.8634 | 40800 | 0.1287 | - | | 0.8655 | 40900 | 0.1797 | - | | 0.8677 | 41000 | 0.1533 | - | | 0.8698 | 41100 | 0.1668 | - | | 0.8719 | 41200 | 0.2047 | - | | 0.8740 | 41300 | 0.1619 | - | | 0.8761 | 41400 | 0.165 | - | | 0.8782 | 41500 | 0.1781 | - | | 0.8803 | 41600 | 0.2221 | - | | 0.8825 | 41700 | 0.2031 | - | | 0.8846 | 41800 | 0.1732 | - | | 0.8867 | 41900 | 0.1599 | - | | 0.8888 | 42000 | 0.1865 | - | | 0.8909 | 42100 | 0.1367 | - | | 0.8930 | 42200 | 0.1469 | - | | 0.8952 | 42300 | 0.1777 | - | | 0.8973 | 42400 | 0.1833 | - | | 0.8994 | 42500 | 0.2102 | - | | 0.9015 | 42600 | 0.164 | - | | 0.9036 | 42700 | 0.1752 | - | | 0.9057 | 42800 | 0.2186 | - | | 0.9079 | 42900 | 0.1824 | - | | 0.9100 | 43000 | 0.1796 | - | | 0.9121 | 43100 | 0.1626 | - | | 0.9142 | 43200 | 0.1623 | - | | 0.9163 | 43300 | 0.2036 | - | | 0.9184 | 43400 | 0.1365 | - | | 0.9206 | 43500 | 0.1792 | - | | 0.9227 | 43600 | 0.1583 | - | | 0.9248 | 43700 | 0.1943 | - | | 0.9269 | 43800 | 0.1931 | - | | 0.9290 | 43900 | 0.1777 | - | | 0.9311 | 44000 | 0.1633 | - | | 0.9333 | 44100 | 0.1841 | - | | 0.9354 | 44200 | 0.1674 | - | | 0.9375 | 44300 | 0.1958 | - | | 0.9396 | 44400 | 0.1831 | - | | 0.9417 | 44500 | 0.1899 | - | | 0.9438 | 44600 | 0.177 | - | | 0.9460 | 44700 | 0.1881 | - | | 0.9481 | 44800 | 0.1643 | - | | 0.9502 | 44900 | 0.1462 | - | | **0.9523** | **45000** | **0.2118** | **0.1719** | | 0.9544 | 45100 | 0.1655 | - | | 0.9565 | 45200 | 0.1567 | - | | 0.9586 | 45300 | 0.1429 | - | | 0.9608 | 45400 | 0.1718 | - | | 0.9629 | 45500 | 0.1549 | - | | 0.9650 | 45600 | 0.1556 | - | | 0.9671 | 45700 | 0.1323 | - | | 0.9692 | 45800 | 0.1988 | - | | 0.9713 | 45900 | 0.15 | - | | 0.9735 | 46000 | 0.1546 | - | | 0.9756 | 46100 | 0.1472 | - | | 0.9777 | 46200 | 0.196 | - | | 0.9798 | 46300 | 0.1913 | - | | 0.9819 | 46400 | 0.2261 | - | | 0.9840 | 46500 | 0.1842 | - | | 0.9862 | 46600 | 0.172 | - | | 0.9883 | 46700 | 0.1925 | - | | 0.9904 | 46800 | 0.1928 | - | | 0.9925 | 46900 | 0.1698 | - | | 0.9946 | 47000 | 0.1778 | - | | 0.9967 | 47100 | 0.1497 | - | | 0.9989 | 47200 | 0.1506 | - | * The bold row denotes the saved checkpoint.
### Framework Versions - Python: 3.12.4 - Sentence Transformers: 3.1.0.dev0 - Transformers: 4.42.4 - PyTorch: 2.3.1+cpu - Accelerate: 0.32.1 - Datasets: 2.20.0 - 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", } ``` #### MultipleNegativesRankingLoss ```bibtex @misc{henderson2017efficient, title={Efficient Natural Language Response Suggestion for Smart Reply}, author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil}, year={2017}, eprint={1705.00652}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```