all-MiniLM-L6-v8-pair_score

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the pairs_three_scores_v5 dataset. 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
• Training Dataset:
  • pairs_three_scores_v5
• 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 = [
    'activated charcoal shampoo',
    'belgian chocolate with cranberries',
    'saw palmetto oil conditioner',
]
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]

Training Details

Training Dataset

pairs_three_scores_v5

• Dataset: pairs_three_scores_v5 at 3d8c457
• Size: 80,000,003 training samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 3 tokens mean: 6.06 tokens max: 12 tokens	min: 3 tokens mean: 5.71 tokens max: 13 tokens	min: 0.0 mean: 0.11 max: 1.0

• Samples:

  sentence1	sentence2	score
  vanilla hair cream	free of paraben hair mask	0.5
  nourishing shampoo	cumin lemon tea	0.0
  safe materials pacifier	facial serum	0.5

• Loss: CoSENTLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "pairwise_cos_sim"
  }
  

Evaluation Dataset

pairs_three_scores_v5

• Dataset: pairs_three_scores_v5 at 3d8c457
• Size: 20,000,001 evaluation samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 3 tokens mean: 6.21 tokens max: 12 tokens	min: 3 tokens mean: 5.75 tokens max: 12 tokens	min: 0.0 mean: 0.11 max: 1.0

• Samples:

  sentence1	sentence2	score
  teddy bear toy	long lasting cat food	0.0
  eva hair treatment	fresh pineapple	0.0
  soft wave hair conditioner	hybrid seat bike	0.0

• Loss: CoSENTLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "pairwise_cos_sim"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 128
• per_device_eval_batch_size: 128
• learning_rate: 2e-05
• num_train_epochs: 1
• 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: 128
• per_device_eval_batch_size: 128
• 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: 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: 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
0.8682	542600	0.9424	-
0.8683	542700	0.968	-
0.8685	542800	0.9711	-
0.8686	542900	0.8668	-
0.8688	543000	0.7776	-
0.8690	543100	0.5938	-
0.8691	543200	0.7416	-
0.8693	543300	1.2082	-
0.8694	543400	0.5481	-
0.8696	543500	0.9383	-
0.8698	543600	0.699	-
0.8699	543700	0.6582	-
0.8701	543800	0.9237	-
0.8702	543900	0.5977	-
0.8704	544000	0.632	-
0.8706	544100	0.819	-
0.8707	544200	0.5877	-
0.8709	544300	0.725	-
0.8710	544400	0.6097	-
0.8712	544500	0.4883	-
0.8714	544600	0.7353	-
0.8715	544700	0.8596	-
0.8717	544800	0.4478	-
0.8718	544900	0.49	-
0.8720	545000	0.6203	-
0.8722	545100	0.6758	-
0.8723	545200	0.959	-
0.8725	545300	1.4645	-
0.8726	545400	0.7873	-
0.8728	545500	0.6609	-
0.8730	545600	0.8173	-
0.8731	545700	1.1416	-
0.8733	545800	0.8406	-
0.8734	545900	0.8781	-
0.8736	546000	0.6507	-
0.8738	546100	1.0332	-
0.8739	546200	0.9044	-
0.8741	546300	0.8617	-
0.8742	546400	0.7377	-
0.8744	546500	0.7668	-
0.8746	546600	0.6856	-
0.8747	546700	1.0069	-
0.8749	546800	0.5628	-
0.8750	546900	0.6661	-
0.8752	547000	0.8508	-
0.8754	547100	1.0595	-
0.8755	547200	0.8156	-
0.8757	547300	0.4535	-
0.8758	547400	0.7963	-
0.8760	547500	0.8964	-
0.8762	547600	0.6343	-
0.8763	547700	0.9795	-
0.8765	547800	1.0885	-
0.8766	547900	0.6333	-
0.8768	548000	1.0065	-
0.8770	548100	0.8155	-
0.8771	548200	0.8595	-
0.8773	548300	1.2973	-
0.8774	548400	0.9477	-
0.8776	548500	1.092	-
0.8778	548600	0.9252	-
0.8779	548700	0.6214	-
0.8781	548800	0.6302	-
0.8782	548900	0.4542	-
0.8784	549000	0.6626	-
0.8786	549100	0.6616	-
0.8787	549200	0.5897	-
0.8789	549300	0.5641	-
0.8790	549400	0.8449	-
0.8792	549500	0.7743	-
0.8794	549600	0.8134	-
0.8795	549700	1.0455	-
0.8797	549800	0.6805	-
0.8798	549900	0.6526	-
0.8800	550000	0.5727	-
0.8802	550100	0.5923	-
0.8803	550200	0.565	-
0.8805	550300	0.7745	-
0.8806	550400	0.757	-
0.8808	550500	0.624	-
0.8810	550600	0.9387	-
0.8811	550700	0.9718	-
0.8813	550800	0.9184	-
0.8814	550900	1.166	-
0.8816	551000	0.6725	-
0.8818	551100	0.9767	-
0.8819	551200	0.517	-
0.8821	551300	0.9126	-
0.8822	551400	1.3649	-
0.8824	551500	0.7633	-
0.8826	551600	0.6029	-
0.8827	551700	0.4923	-
0.8829	551800	0.7787	-
0.8830	551900	0.7437	-
0.8832	552000	0.7627	-
0.8834	552100	0.5648	-
0.8835	552200	0.5564	-
0.8837	552300	0.7376	-
0.8838	552400	0.8405	-
0.8840	552500	1.062	-
0.8842	552600	0.7844	-
0.8843	552700	0.6866	-
0.8845	552800	0.8532	-
0.8846	552900	0.4204	-
0.8848	553000	0.7487	-
0.8850	553100	0.5511	-
0.8851	553200	0.8468	-
0.8853	553300	0.9251	-
0.8854	553400	1.0542	-
0.8856	553500	0.9342	-
0.8858	553600	1.0533	-
0.8859	553700	0.7185	-
0.8861	553800	0.5811	-
0.8862	553900	0.8484	-
0.8864	554000	0.5215	-
0.8866	554100	0.4963	-
0.8867	554200	0.6594	-
0.8869	554300	0.5277	-
0.8870	554400	0.5139	-
0.8872	554500	0.9343	-
0.8874	554600	0.9857	-
0.8875	554700	0.7193	-
0.8877	554800	0.9394	-
0.8878	554900	0.91	-
0.8880	555000	0.601	-
0.8882	555100	0.4681	-
0.8883	555200	0.7671	-
0.8885	555300	0.4485	-
0.8886	555400	0.8482	-
0.8888	555500	0.8826	-
0.8890	555600	0.3257	-
0.8891	555700	0.6727	-
0.8893	555800	0.7098	-
0.8894	555900	0.7871	-
0.8896	556000	0.843	-
0.8898	556100	1.0637	-
0.8899	556200	0.4367	-
0.8901	556300	0.8833	-
0.8902	556400	0.6529	-
0.8904	556500	1.0443	-
0.8906	556600	1.1076	-
0.8907	556700	0.7762	-
0.8909	556800	0.5598	-
0.8910	556900	1.127	-
0.8912	557000	0.5471	-
0.8914	557100	0.869	-
0.8915	557200	0.8392	-
0.8917	557300	0.7547	-
0.8918	557400	0.5796	-
0.8920	557500	0.7446	-
0.8922	557600	0.9913	-
0.8923	557700	0.6937	-
0.8925	557800	0.5643	-
0.8926	557900	0.8484	-
0.8928	558000	0.8971	-
0.8930	558100	1.1094	-
0.8931	558200	0.6835	-
0.8933	558300	0.8818	-
0.8934	558400	1.1366	-
0.8936	558500	0.8887	-
0.8938	558600	0.5754	-
0.8939	558700	0.7777	-
0.8941	558800	0.9033	-
0.8942	558900	0.5612	-
0.8944	559000	0.7949	-
0.8946	559100	1.1081	-
0.8947	559200	0.6708	-
0.8949	559300	0.7044	-
0.8950	559400	0.6862	-
0.8952	559500	0.8251	-
0.8954	559600	0.7551	-
0.8955	559700	1.0697	-
0.8957	559800	0.9638	-
0.8958	559900	0.9433	-
0.8960	560000	0.7142	-
0.8962	560100	0.6868	-
0.8963	560200	1.0483	-
0.8965	560300	0.9234	-
0.8966	560400	1.0903	-
0.8968	560500	0.8217	-
0.8970	560600	0.6451	-
0.8971	560700	0.7644	-
0.8973	560800	0.518	-
0.8974	560900	0.6178	-
0.8976	561000	0.6031	-
0.8978	561100	0.7723	-
0.8979	561200	0.3514	-
0.8981	561300	0.8751	-
0.8982	561400	0.7787	-
0.8984	561500	0.7343	-
0.8986	561600	0.674	-
0.8987	561700	0.8175	-
0.8989	561800	0.7348	-
0.8990	561900	0.8423	-
0.8992	562000	1.004	-
0.8994	562100	0.9213	-
0.8995	562200	1.0421	-
0.8997	562300	0.658	-
0.8998	562400	0.8207	-
0.9000	562500	0.5178	-
0.9002	562600	0.7567	-
0.9003	562700	0.8287	-
0.9005	562800	0.5924	-
0.9006	562900	0.9151	-
0.9008	563000	0.9069	-
0.9010	563100	0.7985	-
0.9011	563200	0.7565	-
0.9013	563300	0.823	-
0.9014	563400	0.5373	-
0.9016	563500	0.5473	-
0.9018	563600	0.7323	-
0.9019	563700	0.691	-
0.9021	563800	0.8818	-
0.9022	563900	0.7351	-
0.9024	564000	1.0715	-
0.9026	564100	0.722	-
0.9027	564200	0.6988	-
0.9029	564300	1.1843	-
0.9030	564400	1.0299	-
0.9032	564500	1.119	-
0.9034	564600	0.6954	-
0.9035	564700	0.8773	-
0.9037	564800	0.7873	-
0.9038	564900	0.7503	-
0.9040	565000	1.1296	-
0.9042	565100	0.777	-
0.9043	565200	0.8982	-
0.9045	565300	0.9224	-
0.9046	565400	0.8596	-
0.9048	565500	0.5435	-
0.9050	565600	0.8324	-
0.9051	565700	0.4121	-
0.9053	565800	0.9148	-
0.9054	565900	0.4525	-
0.9056	566000	0.7476	-
0.9058	566100	0.8766	-
0.9059	566200	1.1123	-
0.9061	566300	0.8109	-
0.9062	566400	0.8251	-
0.9064	566500	0.9638	-
0.9066	566600	0.7842	-
0.9067	566700	0.8727	-
0.9069	566800	1.1777	-
0.9070	566900	1.435	-
0.9072	567000	0.7354	-
0.9074	567100	0.796	-
0.9075	567200	0.8451	-
0.9077	567300	0.479	-
0.9078	567400	0.5299	-
0.9080	567500	0.7735	-
0.9082	567600	1.1211	-
0.9083	567700	0.9364	-
0.9085	567800	0.5533	-
0.9086	567900	0.9091	-
0.9088	568000	0.7493	-
0.9090	568100	1.0247	-
0.9091	568200	0.4836	-
0.9093	568300	0.9966	-
0.9094	568400	0.8997	-
0.9096	568500	0.7764	-
0.9098	568600	0.7193	-
0.9099	568700	0.6184	-
0.9101	568800	0.9031	-
0.9102	568900	0.7061	-
0.9104	569000	1.0852	-
0.9106	569100	1.0778	-
0.9107	569200	0.6463	-
0.9109	569300	0.5569	-
0.9110	569400	0.5566	-
0.9112	569500	0.6489	-
0.9114	569600	0.8065	-
0.9115	569700	0.8123	-
0.9117	569800	0.5946	-
0.9118	569900	0.8424	-
0.9120	570000	0.8987	-
0.9122	570100	0.7266	-
0.9123	570200	0.7386	-
0.9125	570300	0.7266	-
0.9126	570400	0.8668	-
0.9128	570500	0.7228	-
0.9130	570600	0.6914	-
0.9131	570700	0.8578	-
0.9133	570800	0.7019	-
0.9134	570900	0.5146	-
0.9136	571000	0.8236	-
0.9138	571100	0.8977	-
0.9139	571200	0.6571	-
0.9141	571300	0.6818	-
0.9142	571400	0.6226	-
0.9144	571500	1.034	-
0.9146	571600	0.7306	-
0.9147	571700	1.4244	-
0.9149	571800	0.8388	-
0.9150	571900	0.5627	-
0.9152	572000	0.8637	-
0.9154	572100	1.0419	-
0.9155	572200	1.3043	-
0.9157	572300	0.4563	-
0.9158	572400	0.6826	-
0.9160	572500	0.801	-
0.9162	572600	0.82	-
0.9163	572700	0.4677	-
0.9165	572800	0.6236	-
0.9166	572900	0.7783	-
0.9168	573000	0.8284	-
0.9170	573100	0.8253	-
0.9171	573200	1.039	-
0.9173	573300	0.9098	-
0.9174	573400	1.068	-
0.9176	573500	0.6172	-
0.9178	573600	0.6679	-
0.9179	573700	0.8135	-
0.9181	573800	1.1141	-
0.9182	573900	0.8077	-
0.9184	574000	0.7952	-
0.9186	574100	0.8684	-
0.9187	574200	0.518	-
0.9189	574300	0.6675	-
0.9190	574400	0.9315	-
0.9192	574500	0.6984	-
0.9194	574600	0.7571	-
0.9195	574700	0.9037	-
0.9197	574800	0.5965	-
0.9198	574900	0.8542	-
0.9200	575000	0.8226	-
0.9202	575100	0.6057	-
0.9203	575200	0.7658	-
0.9205	575300	0.9765	-
0.9206	575400	0.9145	-
0.9208	575500	0.3843	-
0.9210	575600	0.8603	-
0.9211	575700	0.9048	-
0.9213	575800	0.7786	-
0.9214	575900	0.8639	-
0.9216	576000	0.8909	-
0.9218	576100	0.6091	-
0.9219	576200	0.4416	-
0.9221	576300	0.4569	-
0.9222	576400	0.6638	-
0.9224	576500	0.9033	-
0.9226	576600	0.5351	-
0.9227	576700	0.8799	-
0.9229	576800	1.212	-
0.9230	576900	0.7717	-
0.9232	577000	0.9058	-
0.9234	577100	0.9647	-
0.9235	577200	0.7648	-
0.9237	577300	0.8776	-
0.9238	577400	0.4155	-
0.9240	577500	0.5997	-
0.9242	577600	0.9836	-
0.9243	577700	0.7584	-
0.9245	577800	0.7656	-
0.9246	577900	0.7135	-
0.9248	578000	0.8408	-
0.9250	578100	0.9118	-
0.9251	578200	0.587	-
0.9253	578300	0.9372	-
0.9254	578400	0.674	-
0.9256	578500	0.7524	-
0.9258	578600	0.7039	-
0.9259	578700	0.7397	-
0.9261	578800	0.739	-
0.9262	578900	0.6249	-
0.9264	579000	0.7223	-
0.9266	579100	0.8787	-
0.9267	579200	0.6817	-
0.9269	579300	0.4517	-
0.9270	579400	0.9203	-
0.9272	579500	1.0586	-
0.9274	579600	0.4509	-
0.9275	579700	0.6122	-
0.9277	579800	0.8044	-
0.9278	579900	0.4963	-
0.9280	580000	0.5926	-
0.9282	580100	0.8616	-
0.9283	580200	0.79	-
0.9285	580300	1.1544	-
0.9286	580400	0.6989	-
0.9288	580500	1.3349	-
0.9290	580600	1.2488	-
0.9291	580700	1.171	-
0.9293	580800	0.5529	-
0.9294	580900	0.7977	-
0.9296	581000	0.6397	-
0.9298	581100	1.2556	-
0.9299	581200	0.8389	-
0.9301	581300	0.967	-
0.9302	581400	0.9108	-
0.9304	581500	0.927	-
0.9306	581600	0.8314	-
0.9307	581700	0.8189	-
0.9309	581800	0.5584	-
0.9310	581900	0.8506	-
0.9312	582000	0.9845	-
0.9314	582100	0.8159	-
0.9315	582200	0.6512	-
0.9317	582300	0.7216	-
0.9318	582400	0.7841	-
0.9320	582500	0.852	-
0.9322	582600	0.7754	-
0.9323	582700	0.6775	-
0.9325	582800	0.4598	-
0.9326	582900	0.625	-
0.9328	583000	1.1821	-
0.9330	583100	0.6845	-
0.9331	583200	0.8293	-
0.9333	583300	0.7485	-
0.9334	583400	1.0008	-
0.9336	583500	0.7762	-
0.9338	583600	0.5416	-
0.9339	583700	1.2784	-
0.9341	583800	0.9202	-
0.9342	583900	0.7189	-
0.9344	584000	1.0549	-
0.9346	584100	0.9661	-
0.9347	584200	0.5341	-
0.9349	584300	1.4547	-
0.9350	584400	1.0324	-
0.9352	584500	0.8276	-
0.9354	584600	0.3868	-
0.9355	584700	1.0488	-
0.9357	584800	0.9561	-
0.9358	584900	0.9193	-
0.9360	585000	0.9144	-
0.9362	585100	0.7702	-
0.9363	585200	0.798	-
0.9365	585300	0.5793	-
0.9366	585400	0.7867	-
0.9368	585500	0.8352	-
0.9370	585600	0.6128	-
0.9371	585700	0.734	-
0.9373	585800	0.5431	-
0.9374	585900	0.8416	-
0.9376	586000	0.8711	-
0.9378	586100	0.9059	-
0.9379	586200	0.5545	-
0.9381	586300	0.9609	-
0.9382	586400	0.579	-
0.9384	586500	1.1916	-
0.9386	586600	0.6305	-
0.9387	586700	0.9855	-
0.9389	586800	0.774	-
0.9390	586900	0.6012	-
0.9392	587000	0.7495	-
0.9394	587100	0.6666	-
0.9395	587200	0.8473	-
0.9397	587300	1.0324	-
0.9398	587400	0.6129	-
0.9400	587500	0.8905	-
0.9402	587600	0.6067	-
0.9403	587700	1.0607	-
0.9405	587800	0.6369	-
0.9406	587900	0.6892	-
0.9408	588000	0.6671	-
0.9410	588100	0.7971	-
0.9411	588200	0.7133	-
0.9413	588300	0.46	-
0.9414	588400	0.9073	-
0.9416	588500	0.9276	-
0.9418	588600	1.0273	-
0.9419	588700	0.6709	-
0.9421	588800	0.4284	-
0.9422	588900	0.8745	-
0.9424	589000	0.8677	-
0.9426	589100	0.867	-
0.9427	589200	0.6087	-
0.9429	589300	0.6777	-
0.9430	589400	0.6672	-
0.9432	589500	0.9492	-
0.9434	589600	0.6848	-
0.9435	589700	0.8975	-
0.9437	589800	0.3949	-
0.9438	589900	0.7469	-
0.9440	590000	0.7412	-
0.9442	590100	0.526	-
0.9443	590200	0.4228	-
0.9445	590300	0.9338	-
0.9446	590400	0.6516	-
0.9448	590500	0.9419	-
0.9450	590600	0.755	-
0.9451	590700	0.7699	-
0.9453	590800	0.8904	-
0.9454	590900	0.5596	-
0.9456	591000	0.9401	-
0.9458	591100	0.9583	-
0.9459	591200	0.6807	-
0.9461	591300	0.6972	-
0.9462	591400	0.7217	-
0.9464	591500	0.7406	-
0.9466	591600	0.5819	-
0.9467	591700	0.8508	-
0.9469	591800	0.5315	-
0.9470	591900	0.606	-
0.9472	592000	0.7971	-
0.9474	592100	1.0728	-
0.9475	592200	0.7283	-
0.9477	592300	0.5131	-
0.9478	592400	0.4695	-
0.9480	592500	0.2959	-
0.9482	592600	0.858	-
0.9483	592700	0.5761	-
0.9485	592800	0.9089	-
0.9486	592900	0.6238	-
0.9488	593000	0.5633	-
0.9490	593100	1.0323	-
0.9491	593200	0.6684	-
0.9493	593300	0.8563	-
0.9494	593400	0.7163	-
0.9496	593500	0.7814	-
0.9498	593600	0.4761	-
0.9499	593700	0.5203	-
0.9501	593800	0.9119	-
0.9502	593900	0.8535	-
0.9504	594000	1.0054	-
0.9506	594100	0.8794	-
0.9507	594200	0.6925	-
0.9509	594300	1.0048	-
0.9510	594400	0.7008	-
0.9512	594500	0.7092	-
0.9514	594600	0.803	-
0.9515	594700	0.7868	-
0.9517	594800	0.6047	-
0.9518	594900	0.6654	-
0.9520	595000	0.7418	-
0.9522	595100	1.0645	-
0.9523	595200	0.6193	-
0.9525	595300	0.7615	-
0.9526	595400	0.8291	-
0.9528	595500	0.8298	-
0.9530	595600	0.9187	-
0.9531	595700	0.6942	-
0.9533	595800	0.912	-
0.9534	595900	1.0213	-
0.9536	596000	0.9347	-
0.9538	596100	1.1183	-
0.9539	596200	0.78	-
0.9541	596300	0.8976	-
0.9542	596400	1.0957	-
0.9544	596500	0.8133	-
0.9546	596600	0.6568	-
0.9547	596700	0.8911	-
0.9549	596800	0.5183	-
0.9550	596900	0.7212	-
0.9552	597000	0.888	-
0.9554	597100	0.7661	-
0.9555	597200	0.6028	-
0.9557	597300	1.0602	-
0.9558	597400	0.7299	-
0.9560	597500	0.9885	-
0.9562	597600	0.8964	-
0.9563	597700	0.6961	-
0.9565	597800	0.6989	-
0.9566	597900	1.1453	-
0.9568	598000	0.4009	-
0.9570	598100	0.7645	-
0.9571	598200	0.9124	-
0.9573	598300	0.7354	-
0.9574	598400	0.803	-
0.9576	598500	1.2859	-
0.9578	598600	0.9726	-
0.9579	598700	0.5849	-
0.9581	598800	1.1357	-
0.9582	598900	0.904	-
0.9584	599000	0.6113	-
0.9586	599100	1.0399	-
0.9587	599200	0.8404	-
0.9589	599300	0.945	-
0.9590	599400	0.6225	-
0.9592	599500	0.8617	-
0.9594	599600	0.8782	-
0.9595	599700	0.9332	-
0.9597	599800	0.9949	-
0.9598	599900	0.7016	-
0.9600	600000	0.5833	0.7694
0.9602	600100	0.5462	-
0.9603	600200	0.8458	-
0.9605	600300	0.8256	-
0.9606	600400	0.8134	-
0.9608	600500	0.7465	-
0.9610	600600	1.0022	-
0.9611	600700	0.7794	-
0.9613	600800	0.8742	-
0.9614	600900	0.6161	-
0.9616	601000	1.1433	-
0.9618	601100	0.6988	-
0.9619	601200	0.8715	-
0.9621	601300	0.6198	-
0.9622	601400	0.896	-
0.9624	601500	0.5527	-
0.9626	601600	1.1485	-
0.9627	601700	0.8266	-
0.9629	601800	0.6972	-
0.9630	601900	0.5653	-
0.9632	602000	0.6448	-
0.9634	602100	0.9891	-
0.9635	602200	0.8991	-
0.9637	602300	0.8615	-
0.9638	602400	0.8568	-
0.9640	602500	0.7636	-
0.9642	602600	0.714	-
0.9643	602700	0.5237	-
0.9645	602800	1.1789	-
0.9646	602900	0.5586	-
0.9648	603000	0.5008	-
0.9650	603100	0.8864	-
0.9651	603200	0.8781	-
0.9653	603300	1.0112	-
0.9654	603400	0.9674	-
0.9656	603500	0.5763	-
0.9658	603600	0.4001	-
0.9659	603700	0.69	-
0.9661	603800	0.8321	-
0.9662	603900	0.8196	-
0.9664	604000	0.7085	-
0.9666	604100	0.8921	-
0.9667	604200	0.8983	-
0.9669	604300	1.0145	-
0.9670	604400	1.1885	-
0.9672	604500	0.7833	-
0.9674	604600	1.033	-
0.9675	604700	1.0585	-
0.9677	604800	0.856	-
0.9678	604900	0.4847	-
0.9680	605000	0.7013	-
0.9682	605100	0.7934	-
0.9683	605200	1.1386	-
0.9685	605300	0.6487	-
0.9686	605400	1.0657	-
0.9688	605500	0.432	-
0.9690	605600	0.822	-
0.9691	605700	1.0284	-
0.9693	605800	0.4082	-
0.9694	605900	0.9734	-
0.9696	606000	0.733	-
0.9698	606100	0.608	-
0.9699	606200	0.9526	-
0.9701	606300	0.837	-
0.9702	606400	0.8188	-
0.9704	606500	0.9309	-
0.9706	606600	0.7929	-
0.9707	606700	0.5051	-
0.9709	606800	0.9299	-
0.9710	606900	0.8015	-
0.9712	607000	0.6867	-
0.9714	607100	1.1677	-
0.9715	607200	0.7181	-
0.9717	607300	0.9442	-
0.9718	607400	0.663	-
0.9720	607500	0.7396	-
0.9722	607600	0.8251	-
0.9723	607700	0.6575	-
0.9725	607800	0.6674	-
0.9726	607900	0.7778	-
0.9728	608000	0.6021	-
0.9730	608100	0.9309	-
0.9731	608200	0.8329	-
0.9733	608300	0.9359	-
0.9734	608400	0.7212	-
0.9736	608500	1.0956	-
0.9738	608600	0.6235	-
0.9739	608700	0.6951	-
0.9741	608800	0.7357	-
0.9742	608900	0.427	-
0.9744	609000	1.3058	-
0.9746	609100	0.6824	-
0.9747	609200	0.7743	-
0.9749	609300	0.6551	-
0.9750	609400	0.5327	-
0.9752	609500	0.7648	-
0.9754	609600	0.6966	-
0.9755	609700	0.9422	-
0.9757	609800	1.1221	-
0.9758	609900	0.8919	-
0.9760	610000	0.5507	-
0.9762	610100	0.7228	-
0.9763	610200	0.7117	-
0.9765	610300	0.5439	-
0.9766	610400	1.0969	-
0.9768	610500	0.8394	-
0.9770	610600	1.4258	-
0.9771	610700	0.7213	-
0.9773	610800	0.8785	-
0.9774	610900	0.7981	-
0.9776	611000	0.526	-
0.9778	611100	0.6145	-
0.9779	611200	0.626	-
0.9781	611300	0.6958	-
0.9782	611400	0.7504	-
0.9784	611500	0.7285	-
0.9786	611600	1.0159	-
0.9787	611700	0.5826	-
0.9789	611800	0.7113	-
0.9790	611900	1.166	-
0.9792	612000	1.1578	-
0.9794	612100	0.7783	-
0.9795	612200	0.5356	-
0.9797	612300	0.9754	-
0.9798	612400	0.6884	-
0.9800	612500	0.6951	-
0.9802	612600	0.6126	-
0.9803	612700	0.5493	-
0.9805	612800	0.6776	-
0.9806	612900	0.5393	-
0.9808	613000	0.5629	-
0.9810	613100	0.7929	-
0.9811	613200	0.8572	-
0.9813	613300	1.056	-
0.9814	613400	0.6643	-
0.9816	613500	0.6809	-
0.9818	613600	0.8654	-
0.9819	613700	0.9761	-
0.9821	613800	1.0267	-
0.9822	613900	0.6882	-
0.9824	614000	0.6095	-
0.9826	614100	0.6508	-
0.9827	614200	0.8784	-
0.9829	614300	0.6203	-
0.9830	614400	1.0917	-
0.9832	614500	0.6585	-
0.9834	614600	0.5119	-
0.9835	614700	0.9765	-
0.9837	614800	0.84	-
0.9838	614900	0.6817	-
0.9840	615000	0.8435	-
0.9842	615100	0.6928	-
0.9843	615200	0.6534	-
0.9845	615300	0.5802	-
0.9846	615400	0.8526	-
0.9848	615500	0.841	-
0.9850	615600	0.8053	-
0.9851	615700	0.631	-
0.9853	615800	0.6311	-
0.9854	615900	0.9212	-
0.9856	616000	0.6748	-
0.9858	616100	0.6688	-
0.9859	616200	0.5771	-
0.9861	616300	0.753	-
0.9862	616400	0.7481	-
0.9864	616500	0.842	-
0.9866	616600	0.7109	-
0.9867	616700	0.9474	-
0.9869	616800	0.6522	-
0.9870	616900	0.5251	-
0.9872	617000	0.6909	-
0.9874	617100	0.8574	-
0.9875	617200	0.5703	-
0.9877	617300	0.9685	-
0.9878	617400	0.8947	-
0.9880	617500	0.5895	-
0.9882	617600	1.0236	-
0.9883	617700	0.5926	-
0.9885	617800	0.7436	-
0.9886	617900	0.6056	-
0.9888	618000	0.7208	-
0.9890	618100	0.9684	-
0.9891	618200	0.6403	-
0.9893	618300	0.8872	-
0.9894	618400	0.7158	-
0.9896	618500	0.6708	-
0.9898	618600	0.8817	-
0.9899	618700	0.8722	-
0.9901	618800	0.6972	-
0.9902	618900	0.752	-
0.9904	619000	1.6841	-
0.9906	619100	1.0315	-
0.9907	619200	0.5925	-
0.9909	619300	1.2046	-
0.9910	619400	0.9529	-
0.9912	619500	0.512	-
0.9914	619600	0.9372	-
0.9915	619700	0.8461	-
0.9917	619800	1.0018	-
0.9918	619900	0.8104	-
0.9920	620000	0.9701	-
0.9922	620100	0.9382	-
0.9923	620200	0.7666	-
0.9925	620300	0.5209	-
0.9926	620400	0.5529	-
0.9928	620500	0.8119	-
0.9930	620600	0.7313	-
0.9931	620700	0.7657	-
0.9933	620800	0.7837	-
0.9934	620900	0.7026	-
0.9936	621000	0.7149	-
0.9938	621100	0.6568	-
0.9939	621200	0.7321	-
0.9941	621300	0.7595	-
0.9942	621400	0.6011	-
0.9944	621500	1.2311	-
0.9946	621600	0.4925	-
0.9947	621700	0.8688	-
0.9949	621800	0.4481	-
0.9950	621900	1.0283	-
0.9952	622000	1.2286	-
0.9954	622100	0.873	-
0.9955	622200	0.7679	-
0.9957	622300	0.8617	-
0.9958	622400	0.6354	-
0.9960	622500	0.5432	-
0.9962	622600	1.113	-
0.9963	622700	0.8108	-
0.9965	622800	0.9604	-
0.9966	622900	0.6366	-
0.9968	623000	0.7617	-
0.9970	623100	0.7081	-
0.9971	623200	0.7325	-
0.9973	623300	0.6241	-
0.9974	623400	0.4382	-
0.9976	623500	0.3651	-
0.9978	623600	0.6324	-
0.9979	623700	0.5758	-
0.9981	623800	0.7779	-
0.9982	623900	0.7489	-
0.9984	624000	0.6391	-
0.9986	624100	0.673	-
0.9987	624200	0.7025	-
0.9989	624300	0.871	-
0.9990	624400	1.0238	-
0.9992	624500	0.5088	-
0.9994	624600	0.7578	-
0.9995	624700	0.8879	-
0.9997	624800	1.1698	-
0.9998	624900	1.0531	-
1.0000	625000	0.838	-

Framework Versions

• Python: 3.8.10
• Sentence Transformers: 3.1.1
• Transformers: 4.45.2
• PyTorch: 2.4.1+cu118
• Accelerate: 1.0.1
• Datasets: 3.0.1
• Tokenizers: 0.20.3

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},
}