README.md

metadata

base_model: sentence-transformers/all-MiniLM-L6-v2
language:
  - en
library_name: sentence-transformers
license: apache-2.0
metrics:
  - pearson_cosine
  - spearman_cosine
  - pearson_manhattan
  - spearman_manhattan
  - pearson_euclidean
  - spearman_euclidean
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:757962
  - loss:CoSENTLoss
widget:
  - source_sentence: cozy beanbag
    sentences:
      - black tee
      - bag
      - beige pants
  - source_sentence: lace up top
    sentences:
      - necklace
      - tote bag
      - swimsuit
  - source_sentence: soft beanbag
    sentences:
      - burlap bag
      - bag
      - bag
  - source_sentence: chair beanbag
    sentences:
      - bag
      - cotton cap
      - women swimsuit
  - source_sentence: foam beanbag
    sentences:
      - stretchable luggage cover
      - cycling shorts
      - bag
model-index:
  - name: all-MiniLM-L6-v2-five_scores
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev
          type: sts-dev
        metrics:
          - type: pearson_cosine
            value: 0.17485149631639327
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.09988414865893605
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.17514973425719355
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.10129077593840645
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.17476246568808063
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.09988419374813992
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.17485150231012306
            name: Pearson Dot
          - type: spearman_dot
            value: 0.09988419086282155
            name: Spearman Dot
          - type: pearson_max
            value: 0.17514973425719355
            name: Pearson Max
          - type: spearman_max
            value: 0.10129077593840645
            name: Spearman Max

all-MiniLM-L6-v2-five_scores

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. It maps sentences & paragraphs to a 384-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/all-MiniLM-L6-v2
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 384 tokens
• Similarity Function: Cosine Similarity
• Language: en
• License: apache-2.0

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, '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): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    'foam beanbag',
    'bag',
    'cycling shorts',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# 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

Metric	Value
pearson_cosine	0.1749
spearman_cosine	0.0999
pearson_manhattan	0.1751
spearman_manhattan	0.1013
pearson_euclidean	0.1748
spearman_euclidean	0.0999
pearson_dot	0.1749
spearman_dot	0.0999
pearson_max	0.1751
spearman_max	0.1013

Training Details

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• learning_rate: 2e-05
• num_train_epochs: 4
• warmup_ratio: 0.1
• fp16: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• 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: 2e-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: 4
• 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}
• 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
• use_liger_kernel: False
• eval_use_gather_object: False
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss	loss	sts-dev_spearman_cosine
0	0	-	-	0.0999
0.0042	100	12.0647	-	-
0.0084	200	11.7727	-	-
0.0127	300	11.1315	-	-
0.0169	400	10.8852	-	-
0.0211	500	9.9168	10.4208	-
0.0253	600	9.4099	-	-
0.0296	700	8.5361	-	-
0.0338	800	7.7286	-	-
0.0380	900	7.0852	-	-
0.0422	1000	6.3646	6.6350	-
0.0464	1100	6.1673	-	-
0.0507	1200	5.5683	-	-
0.0549	1300	5.4462	-	-
0.0591	1400	5.303	-	-
0.0633	1500	5.1935	5.2429	-
0.0675	1600	5.1856	-	-
0.0718	1700	5.0136	-	-
0.0760	1800	5.0667	-	-
0.0802	1900	4.9982	-	-
0.0844	2000	5.0429	5.0099	-
0.0887	2100	4.8719	-	-
0.0929	2200	4.8579	-	-
0.0971	2300	4.9282	-	-
0.1013	2400	4.9848	-	-
0.1055	2500	4.8974	4.9078	-
0.1098	2600	4.9103	-	-
0.1140	2700	4.7459	-	-
0.1182	2800	4.8084	-	-
0.1224	2900	4.8221	-	-
0.1267	3000	4.7622	4.8170	-
0.1309	3100	4.7004	-	-
0.1351	3200	4.6912	-	-
0.1393	3300	4.6595	-	-
0.1435	3400	4.7322	-	-
0.1478	3500	4.7575	4.7199	-
0.1520	3600	4.6443	-	-
0.1562	3700	4.6638	-	-
0.1604	3800	4.5958	-	-
0.1646	3900	4.6285	-	-
0.1689	4000	4.6347	4.6554	-
0.1731	4100	4.6558	-	-
0.1773	4200	4.6712	-	-
0.1815	4300	4.6126	-	-
0.1858	4400	4.6219	-	-
0.1900	4500	4.6101	4.6206	-
0.1942	4600	4.7682	-	-
0.1984	4700	4.5385	-	-
0.2026	4800	4.6744	-	-
0.2069	4900	4.5383	-	-
0.2111	5000	4.6095	4.6262	-
0.2153	5100	4.6807	-	-
0.2195	5200	4.4866	-	-
0.2238	5300	4.5353	-	-
0.2280	5400	4.5285	-	-
0.2322	5500	4.5416	4.5914	-
0.2364	5600	4.623	-	-
0.2406	5700	4.5337	-	-
0.2449	5800	4.5726	-	-
0.2491	5900	4.5467	-	-
0.2533	6000	4.3986	4.6011	-
0.2575	6100	4.559	-	-
0.2617	6200	4.6066	-	-
0.2660	6300	4.4445	-	-
0.2702	6400	4.4518	-	-
0.2744	6500	4.4761	4.5093	-
0.2786	6600	4.3362	-	-
0.2829	6700	4.4936	-	-
0.2871	6800	4.2397	-	-
0.2913	6900	4.5243	-	-
0.2955	7000	4.496	4.3969	-
0.2997	7100	4.2558	-	-
0.3040	7200	4.4691	-	-
0.3082	7300	4.4819	-	-
0.3124	7400	4.3785	-	-
0.3166	7500	4.4214	4.4199	-
0.3209	7600	4.4935	-	-
0.3251	7700	4.4238	-	-
0.3293	7800	4.5361	-	-
0.3335	7900	4.4284	-	-
0.3377	8000	4.3918	4.3976	-
0.3420	8100	4.4622	-	-
0.3462	8200	4.4128	-	-
0.3504	8300	4.1565	-	-
0.3546	8400	4.3241	-	-
0.3588	8500	4.2764	4.4261	-
0.3631	8600	4.2101	-	-
0.3673	8700	4.4044	-	-
0.3715	8800	4.254	-	-
0.3757	8900	4.362	-	-
0.3800	9000	4.3424	4.4409	-
0.3842	9100	4.3383	-	-
0.3884	9200	4.4713	-	-
0.3926	9300	4.2773	-	-
0.3968	9400	4.2842	-	-
0.4011	9500	4.3301	4.3454	-
0.4053	9600	4.3224	-	-
0.4095	9700	4.3878	-	-
0.4137	9800	4.3614	-	-
0.4180	9900	4.3423	-	-
0.4222	10000	4.3576	4.3549	-
0.4264	10100	4.1451	-	-
0.4306	10200	4.3326	-	-
0.4348	10300	4.2761	-	-
0.4391	10400	4.2421	-	-
0.4433	10500	4.262	4.3493	-
0.4475	10600	4.1227	-	-
0.4517	10700	4.2365	-	-
0.4559	10800	4.3528	-	-
0.4602	10900	4.077	-	-
0.4644	11000	4.0878	4.3349	-
0.4686	11100	4.4246	-	-
0.4728	11200	4.1019	-	-
0.4771	11300	4.2565	-	-
0.4813	11400	4.3177	-	-
0.4855	11500	4.1283	4.4236	-
0.4897	11600	4.2232	-	-
0.4939	11700	4.2347	-	-
0.4982	11800	4.082	-	-
0.5024	11900	4.2026	-	-
0.5066	12000	4.2687	4.2691	-
0.5108	12100	4.302	-	-
0.5151	12200	4.0474	-	-
0.5193	12300	4.1286	-	-
0.5235	12400	4.3888	-	-
0.5277	12500	4.2339	4.2414	-
0.5319	12600	4.1976	-	-
0.5362	12700	4.1851	-	-
0.5404	12800	4.3969	-	-
0.5446	12900	4.5229	-	-
0.5488	13000	4.2242	4.1389	-
0.5530	13100	4.2804	-	-
0.5573	13200	4.2097	-	-
0.5615	13300	3.9226	-	-
0.5657	13400	4.2274	-	-
0.5699	13500	4.0309	4.2421	-
0.5742	13600	4.3429	-	-
0.5784	13700	4.0352	-	-
0.5826	13800	4.2926	-	-
0.5868	13900	4.3063	-	-
0.5910	14000	4.3172	4.2267	-
0.5953	14100	4.0057	-	-
0.5995	14200	4.2081	-	-
0.6037	14300	4.2408	-	-
0.6079	14400	4.1066	-	-
0.6122	14500	4.1997	4.1798	-
0.6164	14600	4.2364	-	-
0.6206	14700	4.1135	-	-
0.6248	14800	4.0561	-	-
0.6290	14900	4.0347	-	-
0.6333	15000	4.1979	4.2409	-
0.6375	15100	4.0132	-	-
0.6417	15200	4.1131	-	-
0.6459	15300	3.8049	-	-
0.6501	15400	3.9468	-	-
0.6544	15500	4.17	4.1938	-
0.6586	15600	4.2369	-	-
0.6628	15700	4.159	-	-
0.6670	15800	4.1172	-	-
0.6713	15900	4.01	-	-
0.6755	16000	4.0204	4.2796	-
0.6797	16100	4.0013	-	-
0.6839	16200	4.0174	-	-
0.6881	16300	4.0616	-	-
0.6924	16400	3.9944	-	-
0.6966	16500	4.05	4.2132	-
0.7008	16600	4.0769	-	-
0.7050	16700	4.1289	-	-
0.7092	16800	4.0941	-	-
0.7135	16900	4.2556	-	-
0.7177	17000	4.3075	4.1288	-
0.7219	17100	4.0751	-	-
0.7261	17200	4.0711	-	-
0.7304	17300	3.9483	-	-
0.7346	17400	4.3186	-	-
0.7388	17500	3.932	4.1148	-
0.7430	17600	3.8774	-	-
0.7472	17700	4.2312	-	-
0.7515	17800	3.9327	-	-
0.7557	17900	4.2264	-	-
0.7599	18000	3.9723	4.1061	-
0.7641	18100	4.1206	-	-
0.7684	18200	4.1744	-	-
0.7726	18300	3.89	-	-
0.7768	18400	4.1414	-	-
0.7810	18500	4.0286	4.1405	-
0.7852	18600	3.885	-	-
0.7895	18700	4.3785	-	-
0.7937	18800	3.9304	-	-
0.7979	18900	4.0831	-	-
0.8021	19000	4.1698	4.0998	-
0.8063	19100	3.9876	-	-
0.8106	19200	3.9194	-	-
0.8148	19300	3.9222	-	-
0.8190	19400	4.1863	-	-
0.8232	19500	4.0315	4.0778	-
0.8275	19600	3.9286	-	-
0.8317	19700	3.9605	-	-
0.8359	19800	4.1991	-	-
0.8401	19900	4.0311	-	-
0.8443	20000	3.7869	4.1749	-
0.8486	20100	3.9232	-	-
0.8528	20200	4.034	-	-
0.8570	20300	4.2625	-	-
0.8612	20400	3.983	-	-
0.8655	20500	4.2154	4.1057	-
0.8697	20600	4.1696	-	-
0.8739	20700	3.8989	-	-
0.8781	20800	3.9004	-	-
0.8823	20900	4.2134	-	-
0.8866	21000	3.9789	4.0880	-
0.8908	21100	4.2438	-	-
0.8950	21200	3.9271	-	-
0.8992	21300	3.9693	-	-
0.9034	21400	4.0197	-	-
0.9077	21500	4.1802	4.0145	-
0.9119	21600	3.8818	-	-
0.9161	21700	4.1069	-	-
0.9203	21800	3.7999	-	-
0.9246	21900	3.8949	-	-
0.9288	22000	3.9893	4.1313	-
0.9330	22100	4.0918	-	-
0.9372	22200	4.0451	-	-
0.9414	22300	3.9312	-	-
0.9457	22400	4.117	-	-
0.9499	22500	3.883	4.1090	-
0.9541	22600	3.6942	-	-
0.9583	22700	4.1196	-	-
0.9626	22800	3.9292	-	-
0.9668	22900	3.9081	-	-
0.9710	23000	3.8169	4.1232	-
0.9752	23100	3.8342	-	-
0.9794	23200	4.078	-	-
0.9837	23300	4.0002	-	-
0.9879	23400	3.9373	-	-
0.9921	23500	3.8344	4.1565	-
0.9963	23600	4.2827	-	-
1.0005	23700	4.0298	-	-
1.0048	23800	3.9967	-	-
1.0090	23900	3.7508	-	-
1.0132	24000	3.8919	4.0790	-
1.0174	24100	4.0181	-	-
1.0217	24200	3.7934	-	-
1.0259	24300	3.8986	-	-
1.0301	24400	3.9275	-	-
1.0343	24500	3.6911	4.1602	-
1.0385	24600	3.5855	-	-
1.0428	24700	3.7875	-	-
1.0470	24800	3.7999	-	-
1.0512	24900	3.7718	-	-
1.0554	25000	3.8362	4.0381	-
1.0597	25100	3.8076	-	-
1.0639	25200	3.8875	-	-
1.0681	25300	3.9675	-	-
1.0723	25400	3.8451	-	-
1.0765	25500	3.4346	4.1996	-
1.0808	25600	4.0584	-	-
1.0850	25700	3.602	-	-
1.0892	25800	3.673	-	-
1.0934	25900	3.976	-	-
1.0976	26000	3.8768	3.9983	-
1.1019	26100	3.7575	-	-
1.1061	26200	3.8101	-	-
1.1103	26300	4.104	-	-
1.1145	26400	3.7139	-	-
1.1188	26500	4.0391	4.0018	-
1.1230	26600	3.8449	-	-
1.1272	26700	3.7146	-	-
1.1314	26800	4.0576	-	-
1.1356	26900	3.8831	-	-
1.1399	27000	3.8161	4.0019	-
1.1441	27100	3.9283	-	-
1.1483	27200	3.8637	-	-
1.1525	27300	3.701	-	-
1.1568	27400	3.9364	-	-
1.1610	27500	3.7305	3.9959	-
1.1652	27600	3.8542	-	-
1.1694	27700	3.7249	-	-
1.1736	27800	3.7223	-	-
1.1779	27900	3.9777	-	-
1.1821	28000	3.8036	4.0547	-
1.1863	28100	3.8635	-	-
1.1905	28200	3.8523	-	-
1.1947	28300	3.6757	-	-
1.1990	28400	3.7519	-	-
1.2032	28500	3.983	4.0389	-
1.2074	28600	3.8288	-	-
1.2116	28700	3.8074	-	-
1.2159	28800	3.714	-	-
1.2201	28900	3.6594	-	-
1.2243	29000	3.9452	4.0274	-
1.2285	29100	3.9906	-	-
1.2327	29200	3.9826	-	-
1.2370	29300	3.8635	-	-
1.2412	29400	3.9888	-	-
1.2454	29500	3.7248	4.0287	-
1.2496	29600	3.7484	-	-
1.2539	29700	3.9694	-	-
1.2581	29800	4.059	-	-
1.2623	29900	3.9358	-	-
1.2665	30000	3.8575	3.9484	-
1.2707	30100	3.8382	-	-
1.2750	30200	3.73	-	-
1.2792	30300	4.0439	-	-
1.2834	30400	3.8426	-	-
1.2876	30500	3.7062	4.0188	-
1.2918	30600	3.8926	-	-
1.2961	30700	4.0276	-	-
1.3003	30800	3.6359	-	-
1.3045	30900	4.0006	-	-
1.3087	31000	3.8485	4.0019	-
1.3130	31100	3.7892	-	-
1.3172	31200	3.5783	-	-
1.3214	31300	4.0018	-	-
1.3256	31400	3.9542	-	-
1.3298	31500	3.7739	3.9875	-
1.3341	31600	3.8806	-	-
1.3383	31700	4.176	-	-
1.3425	31800	3.826	-	-
1.3467	31900	3.8514	-	-
1.3510	32000	3.8261	3.9716	-
1.3552	32100	3.8825	-	-
1.3594	32200	3.6388	-	-
1.3636	32300	3.7851	-	-
1.3678	32400	3.5687	-	-
1.3721	32500	3.5408	3.9371	-
1.3763	32600	3.6995	-	-
1.3805	32700	3.882	-	-
1.3847	32800	3.8703	-	-
1.3889	32900	3.806	-	-
1.3932	33000	3.7826	3.8901	-
1.3974	33100	3.7853	-	-
1.4016	33200	3.5745	-	-
1.4058	33300	3.5884	-	-
1.4101	33400	3.8678	-	-
1.4143	33500	4.0917	3.9332	-
1.4185	33600	3.7125	-	-
1.4227	33700	3.7298	-	-
1.4269	33800	3.9447	-	-
1.4312	33900	3.7176	-	-
1.4354	34000	3.6765	4.0302	-
1.4396	34100	3.9847	-	-
1.4438	34200	3.7364	-	-
1.4481	34300	3.8246	-	-
1.4523	34400	3.575	-	-
1.4565	34500	3.814	3.9519	-
1.4607	34600	3.8708	-	-
1.4649	34700	3.7277	-	-
1.4692	34800	3.7758	-	-
1.4734	34900	3.6727	-	-
1.4776	35000	3.773	3.9528	-
1.4818	35100	4.0004	-	-
1.4860	35200	3.8468	-	-
1.4903	35300	3.6814	-	-
1.4945	35400	3.8993	-	-
1.4987	35500	3.8841	3.9402	-
1.5029	35600	3.8272	-	-
1.5072	35700	3.584	-	-
1.5114	35800	3.8424	-	-
1.5156	35900	3.7274	-	-
1.5198	36000	3.9671	3.9035	-
1.5240	36100	3.7078	-	-
1.5283	36200	3.7524	-	-
1.5325	36300	3.6992	-	-
1.5367	36400	3.8152	-	-
1.5409	36500	3.9007	3.9785	-
1.5452	36600	3.6302	-	-
1.5494	36700	3.6208	-	-
1.5536	36800	3.6039	-	-
1.5578	36900	3.7039	-	-
1.5620	37000	3.7069	3.9215	-
1.5663	37100	3.7246	-	-
1.5705	37200	3.7269	-	-
1.5747	37300	3.6822	-	-
1.5789	37400	3.7083	-	-
1.5831	37500	3.7095	3.9668	-
1.5874	37600	3.4556	-	-
1.5916	37700	4.0595	-	-
1.5958	37800	3.6583	-	-
1.6000	37900	3.5662	-	-
1.6043	38000	3.6365	3.9035	-
1.6085	38100	3.6313	-	-
1.6127	38200	3.8767	-	-
1.6169	38300	3.9992	-	-
1.6211	38400	3.554	-	-
1.6254	38500	3.6862	3.8900	-
1.6296	38600	3.7638	-	-
1.6338	38700	3.6716	-	-
1.6380	38800	3.8667	-	-
1.6423	38900	3.5304	-	-
1.6465	39000	3.955	3.8894	-
1.6507	39100	3.4049	-	-
1.6549	39200	3.663	-	-
1.6591	39300	4.0267	-	-
1.6634	39400	3.8868	-	-
1.6676	39500	3.8984	3.9277	-
1.6718	39600	3.575	-	-
1.6760	39700	3.6966	-	-
1.6802	39800	4.0533	-	-
1.6845	39900	3.6106	-	-
1.6887	40000	3.6468	3.9425	-
1.6929	40100	3.7145	-	-
1.6971	40200	3.6602	-	-
1.7014	40300	3.5531	-	-
1.7056	40400	3.7857	-	-
1.7098	40500	3.5586	3.8484	-
1.7140	40600	3.7711	-	-
1.7182	40700	3.7135	-	-
1.7225	40800	3.8785	-	-
1.7267	40900	3.5577	-	-
1.7309	41000	3.5783	3.9013	-
1.7351	41100	3.7346	-	-
1.7394	41200	3.5098	-	-
1.7436	41300	4.0181	-	-
1.7478	41400	3.8404	-	-
1.7520	41500	3.6327	3.8684	-
1.7562	41600	3.7503	-	-
1.7605	41700	3.45	-	-
1.7647	41800	3.9138	-	-
1.7689	41900	3.6061	-	-
1.7731	42000	3.6603	3.7956	-
1.7773	42100	3.6722	-	-
1.7816	42200	3.678	-	-
1.7858	42300	3.5802	-	-
1.7900	42400	3.8253	-	-
1.7942	42500	3.7815	3.8192	-
1.7985	42600	3.7021	-	-
1.8027	42700	3.4263	-	-
1.8069	42800	3.8781	-	-
1.8111	42900	3.5784	-	-
1.8153	43000	3.9405	3.8100	-
1.8196	43100	3.5516	-	-
1.8238	43200	3.8322	-	-
1.8280	43300	3.7948	-	-
1.8322	43400	3.6175	-	-
1.8365	43500	3.5256	3.8552	-
1.8407	43600	3.8199	-	-
1.8449	43700	3.6168	-	-
1.8491	43800	3.5648	-	-
1.8533	43900	3.5584	-	-
1.8576	44000	3.7623	3.8202	-
1.8618	44100	3.7884	-	-
1.8660	44200	3.6241	-	-
1.8702	44300	3.4533	-	-
1.8744	44400	3.575	-	-
1.8787	44500	3.6981	3.9080	-
1.8829	44600	3.6384	-	-
1.8871	44700	3.8267	-	-
1.8913	44800	3.5696	-	-
1.8956	44900	3.5189	-	-
1.8998	45000	3.7528	3.8759	-
1.9040	45100	3.7572	-	-
1.9082	45200	3.7283	-	-
1.9124	45300	3.6185	-	-
1.9167	45400	3.5348	-	-
1.9209	45500	3.5366	3.9713	-
1.9251	45600	3.8358	-	-
1.9293	45700	3.7831	-	-
1.9336	45800	3.7524	-	-
1.9378	45900	3.4533	-	-
1.9420	46000	3.4622	3.8907	-
1.9462	46100	3.7096	-	-
1.9504	46200	3.5447	-	-
1.9547	46300	3.601	-	-
1.9589	46400	3.6369	-	-
1.9631	46500	3.8619	3.8416	-
1.9673	46600	3.6623	-	-
1.9715	46700	3.8225	-	-
1.9758	46800	3.9126	-	-
1.9800	46900	3.8429	-	-
1.9842	47000	3.6607	3.8103	-
1.9884	47100	3.5708	-	-
1.9927	47200	3.6346	-	-
1.9969	47300	3.4577	-	-
2.0011	47400	3.4326	-	-
2.0053	47500	3.5431	3.8311	-
2.0095	47600	3.4852	-	-
2.0138	47700	3.4037	-	-
2.0180	47800	3.5685	-	-
2.0222	47900	3.2866	-	-
2.0264	48000	3.3943	3.9447	-
2.0306	48100	3.3675	-	-
2.0349	48200	3.7605	-	-
2.0391	48300	4.0646	-	-
2.0433	48400	3.4634	-	-
2.0475	48500	3.5041	3.8682	-
2.0518	48600	3.6862	-	-
2.0560	48700	3.5486	-	-
2.0602	48800	3.6148	-	-
2.0644	48900	3.3776	-	-
2.0686	49000	3.4514	3.8841	-
2.0729	49100	3.4575	-	-
2.0771	49200	3.4984	-	-
2.0813	49300	3.3978	-	-
2.0855	49400	3.644	-	-
2.0898	49500	3.6412	3.8866	-
2.0940	49600	3.322	-	-
2.0982	49700	3.7186	-	-
2.1024	49800	3.3604	-	-
2.1066	49900	3.7262	-	-
2.1109	50000	3.541	3.8573	-
2.1151	50100	3.4695	-	-
2.1193	50200	3.3366	-	-
2.1235	50300	3.6556	-	-
2.1277	50400	3.4016	-	-
2.1320	50500	3.6733	3.9452	-
2.1362	50600	3.7553	-	-
2.1404	50700	3.6238	-	-
2.1446	50800	3.4566	-	-
2.1489	50900	3.7676	-	-
2.1531	51000	3.4482	3.8958	-
2.1573	51100	3.409	-	-
2.1615	51200	3.9074	-	-
2.1657	51300	3.613	-	-
2.1700	51400	3.4835	-	-
2.1742	51500	3.5494	3.7883	-
2.1784	51600	3.5205	-	-
2.1826	51700	3.4232	-	-
2.1869	51800	3.6539	-	-
2.1911	51900	3.6586	-	-
2.1953	52000	3.3321	3.8934	-
2.1995	52100	3.7712	-	-
2.2037	52200	3.4973	-	-
2.2080	52300	3.5404	-	-
2.2122	52400	3.4815	-	-
2.2164	52500	3.5586	3.8741	-
2.2206	52600	3.5463	-	-
2.2248	52700	3.537	-	-
2.2291	52800	3.5299	-	-
2.2333	52900	3.5967	-	-
2.2375	53000	3.5156	3.8977	-
2.2417	53100	3.6079	-	-
2.2460	53200	3.4492	-	-
2.2502	53300	3.4611	-	-
2.2544	53400	3.1611	-	-
2.2586	53500	3.6554	3.8444	-
2.2628	53600	3.473	-	-
2.2671	53700	3.8362	-	-
2.2713	53800	3.8243	-	-
2.2755	53900	3.2957	-	-
2.2797	54000	3.4227	3.8651	-
2.2840	54100	3.6771	-	-
2.2882	54200	3.5287	-	-
2.2924	54300	3.6393	-	-
2.2966	54400	3.6447	-	-
2.3008	54500	3.1714	3.8695	-
2.3051	54600	3.5703	-	-
2.3093	54700	3.6058	-	-
2.3135	54800	3.3485	-	-
2.3177	54900	3.4143	-	-
2.3219	55000	3.461	3.8285	-
2.3262	55100	3.7676	-	-
2.3304	55200	3.7192	-	-
2.3346	55300	3.3955	-	-
2.3388	55400	3.5533	-	-
2.3431	55500	3.7335	3.7877	-
2.3473	55600	3.3743	-	-
2.3515	55700	3.5598	-	-
2.3557	55800	3.5939	-	-
2.3599	55900	3.6577	-	-
2.3642	56000	3.407	3.7897	-
2.3684	56100	3.5838	-	-
2.3726	56200	3.5182	-	-
2.3768	56300	3.7881	-	-
2.3811	56400	3.772	-	-
2.3853	56500	3.5779	3.8028	-
2.3895	56600	3.4765	-	-
2.3937	56700	3.5122	-	-
2.3979	56800	3.8646	-	-
2.4022	56900	3.4861	-	-
2.4064	57000	3.4486	3.8668	-
2.4106	57100	3.4319	-	-
2.4148	57200	3.5801	-	-
2.4190	57300	3.4412	-	-
2.4233	57400	3.4917	-	-
2.4275	57500	3.8994	3.7693	-
2.4317	57600	3.4321	-	-
2.4359	57700	3.4605	-	-
2.4402	57800	3.5348	-	-
2.4444	57900	3.6156	-	-
2.4486	58000	3.6726	3.7413	-
2.4528	58100	3.4447	-	-
2.4570	58200	3.5318	-	-
2.4613	58300	3.4284	-	-
2.4655	58400	3.3426	-	-
2.4697	58500	3.5549	3.8398	-
2.4739	58600	3.7305	-	-
2.4782	58700	3.4777	-	-
2.4824	58800	3.625	-	-
2.4866	58900	3.8084	-	-
2.4908	59000	3.6772	3.7805	-
2.4950	59100	3.4634	-	-
2.4993	59200	3.5926	-	-
2.5035	59300	3.303	-	-
2.5077	59400	3.5749	-	-
2.5119	59500	3.7852	3.8255	-
2.5161	59600	3.6317	-	-
2.5204	59700	3.3228	-	-
2.5246	59800	3.4541	-	-
2.5288	59900	3.5879	-	-
2.5330	60000	3.6403	3.7744	-
2.5373	60100	3.5289	-	-
2.5415	60200	3.4	-	-
2.5457	60300	3.4026	-	-
2.5499	60400	3.6348	-	-
2.5541	60500	3.3963	3.7309	-
2.5584	60600	3.2838	-	-
2.5626	60700	3.8537	-	-
2.5668	60800	3.3861	-	-
2.5710	60900	3.5289	-	-
2.5753	61000	3.7611	3.7404	-
2.5795	61100	3.3036	-	-
2.5837	61200	3.4874	-	-
2.5879	61300	3.3885	-	-
2.5921	61400	3.6008	-	-
2.5964	61500	3.7175	3.7685	-
2.6006	61600	3.589	-	-
2.6048	61700	3.6725	-	-
2.6090	61800	3.3397	-	-
2.6132	61900	3.562	-	-
2.6175	62000	3.5421	3.7556	-
2.6217	62100	3.462	-	-
2.6259	62200	3.329	-	-
2.6301	62300	3.4274	-	-
2.6344	62400	3.4622	-	-
2.6386	62500	3.2924	3.8314	-
2.6428	62600	3.5465	-	-
2.6470	62700	3.3618	-	-
2.6512	62800	3.2383	-	-
2.6555	62900	3.3542	-	-
2.6597	63000	3.5209	3.7942	-
2.6639	63100	3.4416	-	-
2.6681	63200	3.5881	-	-
2.6724	63300	3.7347	-	-
2.6766	63400	3.815	-	-
2.6808	63500	3.4667	3.7791	-
2.6850	63600	3.342	-	-
2.6892	63700	3.6695	-	-
2.6935	63800	3.4863	-	-
2.6977	63900	3.741	-	-
2.7019	64000	3.6267	3.8010	-
2.7061	64100	3.2939	-	-
2.7103	64200	3.4422	-	-
2.7146	64300	3.7278	-	-
2.7188	64400	3.8691	-	-
2.7230	64500	3.611	3.7172	-
2.7272	64600	3.5474	-	-
2.7315	64700	3.5087	-	-
2.7357	64800	3.4489	-	-
2.7399	64900	3.6549	-	-
2.7441	65000	3.3956	3.7356	-
2.7483	65100	3.5116	-	-
2.7526	65200	3.1777	-	-
2.7568	65300	3.7644	-	-
2.7610	65400	3.6376	-	-
2.7652	65500	3.6153	3.7486	-
2.7695	65600	3.2564	-	-
2.7737	65700	3.5547	-	-
2.7779	65800	3.3283	-	-
2.7821	65900	3.4592	-	-
2.7863	66000	3.7505	3.7252	-
2.7906	66100	3.3761	-	-
2.7948	66200	3.6223	-	-
2.7990	66300	3.4702	-	-
2.8032	66400	3.8666	-	-
2.8074	66500	3.2927	3.7299	-
2.8117	66600	3.5424	-	-
2.8159	66700	3.5487	-	-
2.8201	66800	3.3343	-	-
2.8243	66900	3.3005	-	-
2.8286	67000	3.5036	3.7752	-
2.8328	67100	3.4419	-	-
2.8370	67200	3.3805	-	-
2.8412	67300	3.3591	-	-
2.8454	67400	3.738	-	-
2.8497	67500	3.268	3.7657	-
2.8539	67600	3.4224	-	-
2.8581	67700	3.5734	-	-
2.8623	67800	3.3804	-	-
2.8666	67900	3.594	-	-
2.8708	68000	3.6526	3.7796	-
2.8750	68100	3.7921	-	-
2.8792	68200	3.352	-	-
2.8834	68300	3.7122	-	-
2.8877	68400	3.5739	-	-
2.8919	68500	3.3912	3.7359	-
2.8961	68600	3.8863	-	-
2.9003	68700	3.6851	-	-
2.9045	68800	3.1867	-	-
2.9088	68900	3.2456	-	-
2.9130	69000	3.447	3.7272	-
2.9172	69100	3.3142	-	-
2.9214	69200	3.8019	-	-
2.9257	69300	3.6041	-	-
2.9299	69400	3.6291	-	-
2.9341	69500	3.5412	3.7041	-
2.9383	69600	3.5873	-	-
2.9425	69700	3.6207	-	-
2.9468	69800	3.5858	-	-
2.9510	69900	3.5341	-	-
2.9552	70000	3.6644	3.7406	-
2.9594	70100	3.4947	-	-
2.9637	70200	3.5763	-	-
2.9679	70300	3.6131	-	-
2.9721	70400	3.509	-	-
2.9763	70500	3.4352	3.7116	-
2.9805	70600	3.3115	-	-
2.9848	70700	3.2393	-	-
2.9890	70800	3.3738	-	-
2.9932	70900	3.424	-	-
2.9974	71000	3.7252	3.7152	-
3.0016	71100	3.6013	-	-
3.0059	71200	3.407	-	-
3.0101	71300	3.2695	-	-
3.0143	71400	3.3632	-	-
3.0185	71500	2.95	3.7985	-
3.0228	71600	3.164	-	-
3.0270	71700	3.4829	-	-
3.0312	71800	3.7491	-	-
3.0354	71900	3.7257	-	-
3.0396	72000	3.701	3.7497	-
3.0439	72100	3.105	-	-
3.0481	72200	3.43	-	-
3.0523	72300	3.3014	-	-
3.0565	72400	3.2578	-	-
3.0608	72500	3.4971	3.7966	-
3.0650	72600	3.4542	-	-
3.0692	72700	3.4634	-	-
3.0734	72800	3.6576	-	-
3.0776	72900	3.38	-	-
3.0819	73000	3.4615	3.7337	-
3.0861	73100	3.6838	-	-
3.0903	73200	3.2183	-	-
3.0945	73300	3.3281	-	-
3.0987	73400	3.2304	-	-
3.1030	73500	3.3314	3.7586	-
3.1072	73600	3.0549	-	-
3.1114	73700	3.4578	-	-
3.1156	73800	3.3797	-	-
3.1199	73900	3.4435	-	-
3.1241	74000	3.1522	3.7355	-
3.1283	74100	3.3775	-	-
3.1325	74200	3.5751	-	-
3.1367	74300	3.5017	-	-
3.1410	74400	3.3353	-	-
3.1452	74500	3.5746	3.7411	-
3.1494	74600	3.7003	-	-
3.1536	74700	3.0499	-	-
3.1579	74800	3.3735	-	-
3.1621	74900	3.5844	-	-
3.1663	75000	3.3551	3.8240	-
3.1705	75100	3.262	-	-
3.1747	75200	3.4301	-	-
3.1790	75300	3.464	-	-
3.1832	75400	3.4751	-	-
3.1874	75500	3.5351	3.7465	-
3.1916	75600	3.2933	-	-
3.1958	75700	4.0448	-	-
3.2001	75800	3.4882	-	-
3.2043	75900	3.615	-	-
3.2085	76000	3.1492	3.7142	-
3.2127	76100	3.0458	-	-
3.2170	76200	3.6002	-	-
3.2212	76300	3.3197	-	-
3.2254	76400	3.3113	-	-
3.2296	76500	3.3607	3.7780	-
3.2338	76600	3.3242	-	-
3.2381	76700	3.6477	-	-
3.2423	76800	3.1657	-	-
3.2465	76900	3.0839	-	-
3.2507	77000	3.599	3.7618	-
3.2549	77100	3.1563	-	-
3.2592	77200	3.1867	-	-
3.2634	77300	3.5676	-	-
3.2676	77400	3.6313	-	-
3.2718	77500	3.2504	3.7301	-
3.2761	77600	3.2488	-	-
3.2803	77700	3.0412	-	-
3.2845	77800	3.1514	-	-
3.2887	77900	2.9742	-	-
3.2929	78000	3.395	3.7579	-
3.2972	78100	3.5513	-	-
3.3014	78200	3.3194	-	-
3.3056	78300	3.2702	-	-
3.3098	78400	3.322	-	-
3.3141	78500	3.5357	3.7827	-
3.3183	78600	3.3831	-	-
3.3225	78700	3.3878	-	-
3.3267	78800	3.2869	-	-
3.3309	78900	3.7636	-	-
3.3352	79000	3.4089	3.7984	-
3.3394	79100	3.3371	-	-
3.3436	79200	3.5966	-	-
3.3478	79300	3.8318	-	-
3.3520	79400	3.4452	-	-
3.3563	79500	3.1789	3.7290	-
3.3605	79600	3.1829	-	-
3.3647	79700	3.4624	-	-
3.3689	79800	3.3163	-	-
3.3732	79900	3.2591	-	-
3.3774	80000	3.2375	3.7153	-
3.3816	80100	3.0596	-	-
3.3858	80200	3.2673	-	-
3.3900	80300	3.8284	-	-
3.3943	80400	3.2518	-	-
3.3985	80500	3.4214	3.7572	-
3.4027	80600	3.3534	-	-
3.4069	80700	3.7609	-	-
3.4112	80800	3.7096	-	-
3.4154	80900	2.9755	-	-
3.4196	81000	3.4585	3.7362	-
3.4238	81100	3.5315	-	-
3.4280	81200	3.4276	-	-
3.4323	81300	3.5303	-	-
3.4365	81400	3.2272	-	-
3.4407	81500	2.9614	3.7592	-
3.4449	81600	3.3272	-	-
3.4491	81700	3.548	-	-
3.4534	81800	3.5806	-	-
3.4576	81900	3.2915	-	-
3.4618	82000	3.4571	3.7447	-
3.4660	82100	3.2471	-	-
3.4703	82200	3.3675	-	-
3.4745	82300	3.039	-	-
3.4787	82400	3.1737	-	-
3.4829	82500	3.5937	3.7527	-
3.4871	82600	3.3723	-	-
3.4914	82700	3.5835	-	-
3.4956	82800	3.3739	-	-
3.4998	82900	3.3891	-	-
3.5040	83000	3.5204	3.7398	-
3.5083	83100	3.0925	-	-
3.5125	83200	3.2285	-	-
3.5167	83300	3.4032	-	-
3.5209	83400	3.5367	-	-
3.5251	83500	3.1513	3.7454	-
3.5294	83600	3.292	-	-
3.5336	83700	3.2018	-	-
3.5378	83800	3.4814	-	-
3.5420	83900	3.2591	-	-
3.5462	84000	3.179	3.7722	-
3.5505	84100	3.3408	-	-
3.5547	84200	3.6131	-	-
3.5589	84300	3.2299	-	-
3.5631	84400	3.3005	-	-
3.5674	84500	3.4731	3.7458	-
3.5716	84600	3.2288	-	-
3.5758	84700	3.4384	-	-
3.5800	84800	3.6438	-	-
3.5842	84900	3.3293	-	-
3.5885	85000	3.3555	3.7534	-
3.5927	85100	3.4791	-	-
3.5969	85200	3.1024	-	-
3.6011	85300	3.4605	-	-
3.6054	85400	3.4317	-	-
3.6096	85500	3.2913	3.7037	-
3.6138	85600	3.3377	-	-
3.6180	85700	3.2746	-	-
3.6222	85800	3.4173	-	-
3.6265	85900	3.4623	-	-
3.6307	86000	3.2596	3.7052	-
3.6349	86100	3.2322	-	-
3.6391	86200	3.2082	-	-
3.6433	86300	3.4993	-	-
3.6476	86400	3.3922	-	-
3.6518	86500	3.2275	3.6793	-
3.6560	86600	3.3031	-	-
3.6602	86700	3.2876	-	-
3.6645	86800	3.5403	-	-
3.6687	86900	3.3889	-	-
3.6729	87000	3.3938	3.6927	-
3.6771	87100	3.3169	-	-
3.6813	87200	3.1372	-	-
3.6856	87300	3.0958	-	-
3.6898	87400	3.1186	-	-
3.6940	87500	3.5419	3.6852	-
3.6982	87600	3.6208	-	-
3.7025	87700	3.3815	-	-
3.7067	87800	2.9388	-	-
3.7109	87900	3.2111	-	-
3.7151	88000	3.4742	3.6905	-
3.7193	88100	3.2668	-	-
3.7236	88200	3.439	-	-
3.7278	88300	3.3342	-	-
3.7320	88400	3.5079	-	-
3.7362	88500	3.4446	3.7126	-
3.7404	88600	3.3036	-	-
3.7447	88700	3.323	-	-
3.7489	88800	3.2921	-	-
3.7531	88900	3.3972	-	-
3.7573	89000	3.3132	3.7031	-
3.7616	89100	3.6181	-	-
3.7658	89200	3.41	-	-
3.7700	89300	3.2602	-	-
3.7742	89400	3.3742	-	-
3.7784	89500	3.2929	3.7064	-
3.7827	89600	3.1366	-	-
3.7869	89700	3.5312	-	-
3.7911	89800	3.2735	-	-
3.7953	89900	3.3797	-	-
3.7996	90000	3.3003	3.7135	-
3.8038	90100	3.483	-	-
3.8080	90200	3.2309	-	-
3.8122	90300	3.3767	-	-
3.8164	90400	2.8296	-	-
3.8207	90500	3.361	3.7145	-
3.8249	90600	3.3726	-	-
3.8291	90700	3.2925	-	-
3.8333	90800	3.5113	-	-
3.8375	90900	3.6037	-	-
3.8418	91000	3.0925	3.7223	-
3.8460	91100	3.4363	-	-
3.8502	91200	3.3181	-	-
3.8544	91300	3.4216	-	-
3.8587	91400	3.1301	-	-
3.8629	91500	3.5791	3.7144	-
3.8671	91600	3.0492	-	-
3.8713	91700	3.4513	-	-
3.8755	91800	3.7442	-	-
3.8798	91900	3.1566	-	-
3.8840	92000	3.3871	3.7025	-
3.8882	92100	3.3478	-	-
3.8924	92200	3.2922	-	-
3.8967	92300	3.0988	-	-
3.9009	92400	3.4383	-	-
3.9051	92500	3.175	3.7026	-
3.9093	92600	3.3831	-	-
3.9135	92700	3.3871	-	-
3.9178	92800	3.5747	-	-
3.9220	92900	3.272	-	-
3.9262	93000	3.4294	3.6876	-
3.9304	93100	3.6332	-	-
3.9346	93200	3.626	-	-
3.9389	93300	3.5402	-	-
3.9431	93400	3.348	-	-
3.9473	93500	3.2556	3.6902	-
3.9515	93600	3.5298	-	-
3.9558	93700	3.5247	-	-
3.9600	93800	3.0763	-	-
3.9642	93900	3.2457	-	-
3.9684	94000	3.1805	3.6897	-
3.9726	94100	3.3959	-	-
3.9769	94200	3.205	-	-
3.9811	94300	3.3307	-	-
3.9853	94400	3.0448	-	-
3.9895	94500	3.0447	3.6906	-
3.9938	94600	3.3314	-	-
3.9980	94700	3.4516	-	-

Framework Versions

• Python: 3.8.10
• Sentence Transformers: 3.1.1
• Transformers: 4.45.1
• PyTorch: 2.4.0+cu121
• Accelerate: 0.34.2
• Datasets: 3.0.1
• Tokenizers: 0.20.0

Citation

BibTeX

Sentence Transformers

@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",
}

CoSENTLoss

@online{kexuefm-8847,
    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
    author={Su Jianlin},
    year={2022},
    month={Jan},
    url={https://kexue.fm/archives/8847},
}