checkpoint-100500/README.md

metadata

base_model: sentence-transformers/all-MiniLM-L6-v2
datasets:
  - youssefkhalil320/pairs_three_scores_v5
language:
  - en
library_name: sentence-transformers
license: apache-2.0
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:80000003
  - loss:CoSENTLoss
widget:
  - source_sentence: durable pvc swim ring
    sentences:
      - flaky croissant
      - urban shoes
      - warm drinks mug
  - source_sentence: iso mak retard capsules
    sentences:
      - savory baguette
      - shea butter body cream
      - softwheeled cruiser
  - source_sentence: love sandra potty
    sentences:
      - utensil holder
      - olive pants
      - headwear
  - source_sentence: dusky hair brush
    sentences:
      - back compartment laptop
      - rubber feet platter
      - honed blade knife
  - source_sentence: nkd skn
    sentences:
      - fruit fragrances nail polish remover
      - panini salmon
      - hand drawing bag

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 = [
    'nkd skn',
    'hand drawing bag',
    'panini salmon',
]
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
0.0002	100	10.8792
0.0003	200	10.9284
0.0005	300	10.6466
0.0006	400	10.841
0.0008	500	10.8094
0.0010	600	10.4323
0.0011	700	10.3032
0.0013	800	10.4006
0.0014	900	10.4743
0.0016	1000	10.2334
0.0018	1100	10.0135
0.0019	1200	9.7874
0.0021	1300	9.7419
0.0022	1400	9.7412
0.0024	1500	9.4585
0.0026	1600	9.5339
0.0027	1700	9.4345
0.0029	1800	9.1733
0.0030	1900	8.9952
0.0032	2000	8.9669
0.0034	2100	8.8152
0.0035	2200	8.7936
0.0037	2300	8.6771
0.0038	2400	8.4648
0.0040	2500	8.5764
0.0042	2600	8.4587
0.0043	2700	8.2966
0.0045	2800	8.2329
0.0046	2900	8.1415
0.0048	3000	8.0404
0.0050	3100	7.9698
0.0051	3200	7.9205
0.0053	3300	7.8314
0.0054	3400	7.8369
0.0056	3500	7.6403
0.0058	3600	7.5842
0.0059	3700	7.5812
0.0061	3800	7.4335
0.0062	3900	7.4917
0.0064	4000	7.3204
0.0066	4100	7.2971
0.0067	4200	7.2233
0.0069	4300	7.2081
0.0070	4400	7.1364
0.0072	4500	7.0663
0.0074	4600	6.9601
0.0075	4700	6.9546
0.0077	4800	6.9019
0.0078	4900	6.8801
0.0080	5000	6.7734
0.0082	5100	6.7648
0.0083	5200	6.7498
0.0085	5300	6.6872
0.0086	5400	6.6264
0.0088	5500	6.579
0.0090	5600	6.6001
0.0091	5700	6.5971
0.0093	5800	6.4694
0.0094	5900	6.3983
0.0096	6000	6.4477
0.0098	6100	6.4308
0.0099	6200	6.4248
0.0101	6300	6.2642
0.0102	6400	6.2763
0.0104	6500	6.3878
0.0106	6600	6.2601
0.0107	6700	6.1789
0.0109	6800	6.1773
0.0110	6900	6.1439
0.0112	7000	6.1863
0.0114	7100	6.0513
0.0115	7200	6.0671
0.0117	7300	6.0212
0.0118	7400	6.0043
0.0120	7500	6.0166
0.0122	7600	5.9754
0.0123	7700	5.9211
0.0125	7800	5.7867
0.0126	7900	5.8534
0.0128	8000	5.7708
0.0130	8100	5.8328
0.0131	8200	5.7417
0.0133	8300	5.8097
0.0134	8400	5.7578
0.0136	8500	5.643
0.0138	8600	5.6401
0.0139	8700	5.6627
0.0141	8800	5.6167
0.0142	8900	5.6539
0.0144	9000	5.4513
0.0146	9100	5.4132
0.0147	9200	5.4714
0.0149	9300	5.4786
0.0150	9400	5.3928
0.0152	9500	5.4774
0.0154	9600	5.2881
0.0155	9700	5.3699
0.0157	9800	5.1483
0.0158	9900	5.3051
0.0160	10000	5.2546
0.0162	10100	5.2314
0.0163	10200	5.1783
0.0165	10300	5.2074
0.0166	10400	5.2825
0.0168	10500	5.1715
0.0170	10600	5.087
0.0171	10700	5.082
0.0173	10800	4.9111
0.0174	10900	5.0213
0.0176	11000	4.9898
0.0178	11100	4.7734
0.0179	11200	4.9511
0.0181	11300	5.0481
0.0182	11400	4.8441
0.0184	11500	4.873
0.0186	11600	4.9988
0.0187	11700	4.7653
0.0189	11800	4.804
0.0190	11900	4.8288
0.0192	12000	4.7053
0.0194	12100	4.6887
0.0195	12200	4.7832
0.0197	12300	4.6817
0.0198	12400	4.6252
0.0200	12500	4.5936
0.0202	12600	4.7452
0.0203	12700	4.5321
0.0205	12800	4.4964
0.0206	12900	4.4421
0.0208	13000	4.3782
0.0210	13100	4.5169
0.0211	13200	4.533
0.0213	13300	4.3725
0.0214	13400	4.2911
0.0216	13500	4.2261
0.0218	13600	4.2467
0.0219	13700	4.1558
0.0221	13800	4.2794
0.0222	13900	4.2383
0.0224	14000	4.1654
0.0226	14100	4.158
0.0227	14200	4.1299
0.0229	14300	4.1902
0.0230	14400	3.7853
0.0232	14500	4.0514
0.0234	14600	4.1655
0.0235	14700	4.051
0.0237	14800	4.078
0.0238	14900	4.1193
0.0240	15000	4.1536
0.0242	15100	3.935
0.0243	15200	3.9535
0.0245	15300	3.7051
0.0246	15400	3.8329
0.0248	15500	3.9412
0.0250	15600	3.6668
0.0251	15700	3.7758
0.0253	15800	3.8805
0.0254	15900	3.8848
0.0256	16000	3.75
0.0258	16100	3.5685
0.0259	16200	3.7016
0.0261	16300	4.0955
0.0262	16400	3.7577
0.0264	16500	3.7485
0.0266	16600	3.8263
0.0267	16700	3.6922
0.0269	16800	3.6568
0.0270	16900	3.7317
0.0272	17000	3.5089
0.0274	17100	3.7377
0.0275	17200	3.6206
0.0277	17300	3.3702
0.0278	17400	3.5126
0.0280	17500	3.4841
0.0282	17600	3.1464
0.0283	17700	3.7012
0.0285	17800	3.5802
0.0286	17900	3.4952
0.0288	18000	3.1174
0.0290	18100	3.3134
0.0291	18200	3.3578
0.0293	18300	3.0209
0.0294	18400	3.3796
0.0296	18500	3.2287
0.0298	18600	3.1537
0.0299	18700	2.9073
0.0301	18800	3.3444
0.0302	18900	3.1341
0.0304	19000	2.8862
0.0306	19100	3.2033
0.0307	19200	3.2764
0.0309	19300	3.0725
0.0310	19400	3.0436
0.0312	19500	3.3493
0.0314	19600	3.0141
0.0315	19700	2.779
0.0317	19800	3.3543
0.0318	19900	3.1526
0.0320	20000	2.7896
0.0322	20100	2.9398
0.0323	20200	3.1254
0.0325	20300	2.8832
0.0326	20400	3.0542
0.0328	20500	2.9722
0.0330	20600	2.9321
0.0331	20700	2.6448
0.0333	20800	3.4006
0.0334	20900	3.0022
0.0336	21000	2.6366
0.0338	21100	3.0112
0.0339	21200	2.7856
0.0341	21300	3.0967
0.0342	21400	2.8754
0.0344	21500	3.1269
0.0346	21600	2.8235
0.0347	21700	2.4912
0.0349	21800	2.5079
0.0350	21900	3.2942
0.0352	22000	2.4184
0.0354	22100	2.782
0.0355	22200	2.7652
0.0357	22300	3.113
0.0358	22400	2.7451
0.0360	22500	2.7473
0.0362	22600	2.5116
0.0363	22700	2.8531
0.0365	22800	2.9171
0.0366	22900	2.7954
0.0368	23000	2.5376
0.0370	23100	3.2488
0.0371	23200	2.6131
0.0373	23300	3.1343
0.0374	23400	2.3159
0.0376	23500	2.4225
0.0378	23600	2.5034
0.0379	23700	3.0067
0.0381	23800	2.313
0.0382	23900	2.5363
0.0384	24000	2.7929
0.0386	24100	2.617
0.0387	24200	2.9711
0.0389	24300	2.7726
0.0390	24400	2.5849
0.0392	24500	2.3231
0.0394	24600	2.2477
0.0395	24700	2.5487
0.0397	24800	2.5175
0.0398	24900	2.6758
0.0400	25000	2.7313
0.0402	25100	2.4846
0.0403	25200	2.8697
0.0405	25300	2.5289
0.0406	25400	2.235
0.0408	25500	2.5028
0.0410	25600	2.6295
0.0411	25700	2.6159
0.0413	25800	2.4447
0.0414	25900	2.7233
0.0416	26000	2.5651
0.0418	26100	2.1317
0.0419	26200	2.6157
0.0421	26300	2.7385
0.0422	26400	2.4642
0.0424	26500	2.0621
0.0426	26600	2.3864
0.0427	26700	2.6951
0.0429	26800	2.2628
0.0430	26900	2.7538
0.0432	27000	2.6871
0.0434	27100	2.2453
0.0435	27200	1.6334
0.0437	27300	2.666
0.0438	27400	2.128
0.0440	27500	2.7573
0.0442	27600	2.5276
0.0443	27700	2.2438
0.0445	27800	2.3156
0.0446	27900	2.1735
0.0448	28000	2.1733
0.0450	28100	2.4094
0.0451	28200	2.8484
0.0453	28300	2.4507
0.0454	28400	2.6822
0.0456	28500	2.1191
0.0458	28600	2.0696
0.0459	28700	2.4027
0.0461	28800	1.7958
0.0462	28900	2.5874
0.0464	29000	2.2679
0.0466	29100	2.6394
0.0467	29200	1.7998
0.0469	29300	2.6834
0.0470	29400	2.1242
0.0472	29500	2.0039
0.0474	29600	2.018
0.0475	29700	2.9357
0.0477	29800	2.1914
0.0478	29900	2.0968
0.0480	30000	1.9762
0.0482	30100	2.1436
0.0483	30200	2.1919
0.0485	30300	1.9683
0.0486	30400	2.3543
0.0488	30500	2.0642
0.0490	30600	1.8447
0.0491	30700	2.3467
0.0493	30800	2.6461
0.0494	30900	2.028
0.0496	31000	1.4188
0.0498	31100	2.7219
0.0499	31200	2.2345
0.0501	31300	2.201
0.0502	31400	2.092
0.0504	31500	2.2871
0.0506	31600	2.0167
0.0507	31700	1.9175
0.0509	31800	2.2229
0.0510	31900	2.1196
0.0512	32000	2.2192
0.0514	32100	1.6462
0.0515	32200	2.099
0.0517	32300	2.0914
0.0518	32400	2.3295
0.0520	32500	2.256
0.0522	32600	1.7662
0.0523	32700	1.7234
0.0525	32800	1.984
0.0526	32900	2.1815
0.0528	33000	1.4987
0.0530	33100	2.0034
0.0531	33200	2.6008
0.0533	33300	2.4585
0.0534	33400	1.881
0.0536	33500	1.8738
0.0538	33600	1.9726
0.0539	33700	2.3734
0.0541	33800	1.6898
0.0542	33900	2.2171
0.0544	34000	1.4453
0.0546	34100	1.5057
0.0547	34200	2.1497
0.0549	34300	1.8618
0.0550	34400	1.7878
0.0552	34500	1.8199
0.0554	34600	2.1649
0.0555	34700	1.7906
0.0557	34800	1.6816
0.0558	34900	2.1464
0.0560	35000	2.0039
0.0562	35100	1.735
0.0563	35200	1.853
0.0565	35300	1.6068
0.0566	35400	1.6349
0.0568	35500	1.9571
0.0570	35600	1.5854
0.0571	35700	1.9756
0.0573	35800	1.9816
0.0574	35900	1.6758
0.0576	36000	2.2583
0.0578	36100	1.7584
0.0579	36200	1.9894
0.0581	36300	2.3922
0.0582	36400	2.0077
0.0584	36500	2.3684
0.0586	36600	2.1103
0.0587	36700	2.0728
0.0589	36800	1.9364
0.0590	36900	2.5203
0.0592	37000	1.8473
0.0594	37100	1.8076
0.0595	37200	2.0157
0.0597	37300	2.1587
0.0598	37400	1.9825
0.0600	37500	2.0693
0.0602	37600	1.5505
0.0603	37700	1.5472
0.0605	37800	2.0568
0.0606	37900	1.9219
0.0608	38000	2.091
0.0610	38100	2.0523
0.0611	38200	1.7628
0.0613	38300	1.8753
0.0614	38400	1.846
0.0616	38500	1.803
0.0618	38600	2.1226
0.0619	38700	2.0906
0.0621	38800	1.4321
0.0622	38900	2.5214
0.0624	39000	1.5412
0.0626	39100	1.4382
0.0627	39200	1.8417
0.0629	39300	2.1105
0.0630	39400	1.6347
0.0632	39500	2.0372
0.0634	39600	1.6222
0.0635	39700	1.8033
0.0637	39800	1.9847
0.0638	39900	2.1354
0.0640	40000	1.6792
0.0642	40100	2.1055
0.0643	40200	2.0657
0.0645	40300	1.9618
0.0646	40400	1.5807
0.0648	40500	1.6451
0.0650	40600	2.1299
0.0651	40700	1.9912
0.0653	40800	1.6392
0.0654	40900	1.8049
0.0656	41000	1.9832
0.0658	41100	2.0309
0.0659	41200	1.8362
0.0661	41300	2.2709
0.0662	41400	2.0785
0.0664	41500	1.5627
0.0666	41600	1.6058
0.0667	41700	1.7099
0.0669	41800	1.7096
0.0670	41900	1.6429
0.0672	42000	1.2514
0.0674	42100	1.5746
0.0675	42200	1.7186
0.0677	42300	1.8152
0.0678	42400	1.705
0.0680	42500	1.6779
0.0682	42600	1.8157
0.0683	42700	1.8464
0.0685	42800	1.748
0.0686	42900	1.6836
0.0688	43000	1.65
0.0690	43100	1.5632
0.0691	43200	2.0987
0.0693	43300	1.5783
0.0694	43400	1.8029
0.0696	43500	1.7154
0.0698	43600	1.663
0.0699	43700	1.4403
0.0701	43800	1.6513
0.0702	43900	2.2041
0.0704	44000	2.3908
0.0706	44100	1.7153
0.0707	44200	2.2112
0.0709	44300	1.8663
0.0710	44400	1.8206
0.0712	44500	2.2269
0.0714	44600	1.8159
0.0715	44700	1.9257
0.0717	44800	2.087
0.0718	44900	1.3623
0.0720	45000	1.5747
0.0722	45100	1.8051
0.0723	45200	2.3691
0.0725	45300	2.1125
0.0726	45400	1.566
0.0728	45500	1.5042
0.0730	45600	1.9469
0.0731	45700	1.9346
0.0733	45800	1.4362
0.0734	45900	1.9164
0.0736	46000	1.511
0.0738	46100	1.4523
0.0739	46200	1.1247
0.0741	46300	1.9694
0.0742	46400	2.1909
0.0744	46500	2.0247
0.0746	46600	1.2061
0.0747	46700	1.6151
0.0749	46800	1.6184
0.0750	46900	2.0375
0.0752	47000	1.8357
0.0754	47100	1.7605
0.0755	47200	2.1139
0.0757	47300	1.2971
0.0758	47400	1.7242
0.0760	47500	1.2726
0.0762	47600	1.9947
0.0763	47700	2.2796
0.0765	47800	1.6232
0.0766	47900	1.3513
0.0768	48000	1.291
0.0770	48100	1.5954
0.0771	48200	1.6232
0.0773	48300	1.8858
0.0774	48400	1.6235
0.0776	48500	1.9061
0.0778	48600	1.5919
0.0779	48700	1.8474
0.0781	48800	1.7112
0.0782	48900	1.8007
0.0784	49000	1.7499
0.0786	49100	1.4046
0.0787	49200	2.0843
0.0789	49300	1.52
0.0790	49400	1.8708
0.0792	49500	1.673
0.0794	49600	1.8457
0.0795	49700	1.5627
0.0797	49800	1.6497
0.0798	49900	1.5787
0.0800	50000	1.8507
0.0802	50100	1.4336
0.0803	50200	2.152
0.0805	50300	1.6311
0.0806	50400	1.7442
0.0808	50500	1.8063
0.0810	50600	1.4
0.0811	50700	1.6401
0.0813	50800	1.9426
0.0814	50900	2.0937
0.0816	51000	1.8187
0.0818	51100	2.1751
0.0819	51200	2.1703
0.0821	51300	1.4443
0.0822	51400	1.9266
0.0824	51500	1.8226
0.0826	51600	1.4394
0.0827	51700	1.052
0.0829	51800	1.0614
0.0830	51900	1.4591
0.0832	52000	1.6479
0.0834	52100	1.7548
0.0835	52200	1.6293
0.0837	52300	1.7183
0.0838	52400	1.2329
0.0840	52500	1.5292
0.0842	52600	1.6752
0.0843	52700	1.3228
0.0845	52800	1.485
0.0846	52900	1.4228
0.0848	53000	1.1385
0.0850	53100	1.1812
0.0851	53200	1.4763
0.0853	53300	1.9444
0.0854	53400	1.5316
0.0856	53500	1.6928
0.0858	53600	1.4466
0.0859	53700	1.438
0.0861	53800	1.1629
0.0862	53900	1.3017
0.0864	54000	1.6614
0.0866	54100	1.4535
0.0867	54200	1.7061
0.0869	54300	1.4681
0.0870	54400	1.3449
0.0872	54500	1.8814
0.0874	54600	1.5989
0.0875	54700	1.3711
0.0877	54800	1.3199
0.0878	54900	1.3713
0.0880	55000	1.441
0.0882	55100	1.268
0.0883	55200	1.1648
0.0885	55300	1.8108
0.0886	55400	1.4904
0.0888	55500	1.2555
0.0890	55600	1.2733
0.0891	55700	1.5194
0.0893	55800	1.7587
0.0894	55900	1.6183
0.0896	56000	1.3596
0.0898	56100	1.5248
0.0899	56200	1.5177
0.0901	56300	1.7579
0.0902	56400	1.5508
0.0904	56500	1.5965
0.0906	56600	1.5762
0.0907	56700	1.7441
0.0909	56800	2.0257
0.0910	56900	1.1371
0.0912	57000	1.8825
0.0914	57100	1.0455
0.0915	57200	1.5889
0.0917	57300	1.192
0.0918	57400	1.5374
0.0920	57500	1.6236
0.0922	57600	1.8945
0.0923	57700	1.607
0.0925	57800	1.8133
0.0926	57900	1.5777
0.0928	58000	1.5043
0.0930	58100	1.7681
0.0931	58200	1.623
0.0933	58300	2.2137
0.0934	58400	2.2447
0.0936	58500	2.3013
0.0938	58600	1.3105
0.0939	58700	1.4461
0.0941	58800	2.1321
0.0942	58900	1.7541
0.0944	59000	1.7894
0.0946	59100	1.693
0.0947	59200	1.7073
0.0949	59300	2.0305
0.0950	59400	1.3684
0.0952	59500	1.8754
0.0954	59600	2.0225
0.0955	59700	2.1975
0.0957	59800	1.7173
0.0958	59900	1.4302
0.0960	60000	1.2497
0.0962	60100	1.4058
0.0963	60200	1.0956
0.0965	60300	1.3731
0.0966	60400	1.2953
0.0968	60500	1.0987
0.0970	60600	1.5104
0.0971	60700	1.5224
0.0973	60800	1.3982
0.0974	60900	1.2785
0.0976	61000	1.6018
0.0978	61100	1.4968
0.0979	61200	1.2423
0.0981	61300	1.9973
0.0982	61400	1.2149
0.0984	61500	1.731
0.0986	61600	1.2889
0.0987	61700	1.856
0.0989	61800	0.8942
0.0990	61900	1.3371
0.0992	62000	1.5222
0.0994	62100	1.5435
0.0995	62200	1.1172
0.0997	62300	1.6024
0.0998	62400	1.3914
0.1000	62500	1.4714
0.1002	62600	1.2922
0.1003	62700	1.4263
0.1005	62800	1.4586
0.1006	62900	1.6312
0.1008	63000	1.9607
0.1010	63100	1.5771
0.1011	63200	1.6721
0.1013	63300	1.8461
0.1014	63400	1.5256
0.1016	63500	1.9736
0.1018	63600	1.4735
0.1019	63700	1.4619
0.1021	63800	1.6571
0.1022	63900	1.5888
0.1024	64000	2.0457
0.1026	64100	1.7843
0.1027	64200	1.5116
0.1029	64300	1.6682
0.1030	64400	1.2137
0.1032	64500	1.1308
0.1034	64600	2.031
0.1035	64700	1.6903
0.1037	64800	1.3365
0.1038	64900	1.5736
0.1040	65000	1.7264
0.1042	65100	1.1781
0.1043	65200	1.2503
0.1045	65300	0.9432
0.1046	65400	1.264
0.1048	65500	1.2086
0.1050	65600	1.8692
0.1051	65700	1.2745
0.1053	65800	1.6839
0.1054	65900	1.4509
0.1056	66000	1.1615
0.1058	66100	1.4458
0.1059	66200	1.8329
0.1061	66300	1.567
0.1062	66400	1.6746
0.1064	66500	1.65
0.1066	66600	1.5497
0.1067	66700	1.4009
0.1069	66800	2.058
0.1070	66900	1.6306
0.1072	67000	1.4377
0.1074	67100	1.4501
0.1075	67200	1.2648
0.1077	67300	1.3186
0.1078	67400	1.1313
0.1080	67500	2.2523
0.1082	67600	1.9146
0.1083	67700	1.7334
0.1085	67800	1.7195
0.1086	67900	1.4661
0.1088	68000	1.3503
0.1090	68100	1.0129
0.1091	68200	1.6036
0.1093	68300	0.9312
0.1094	68400	1.5817
0.1096	68500	1.2024
0.1098	68600	0.985
0.1099	68700	1.1712
0.1101	68800	1.5874
0.1102	68900	1.8551
0.1104	69000	1.232
0.1106	69100	1.4688
0.1107	69200	1.1107
0.1109	69300	1.6495
0.1110	69400	1.6278
0.1112	69500	1.7135
0.1114	69600	1.5108
0.1115	69700	1.4056
0.1117	69800	0.9324
0.1118	69900	1.3613
0.1120	70000	1.5283
0.1122	70100	1.3809
0.1123	70200	1.5552
0.1125	70300	1.4567
0.1126	70400	1.4404
0.1128	70500	1.1805
0.1130	70600	2.514
0.1131	70700	1.4821
0.1133	70800	1.5156
0.1134	70900	1.5925
0.1136	71000	1.9517
0.1138	71100	1.2685
0.1139	71200	1.6314
0.1141	71300	1.5252
0.1142	71400	1.5176
0.1144	71500	1.3461
0.1146	71600	1.3832
0.1147	71700	1.2962
0.1149	71800	1.5179
0.1150	71900	1.1041
0.1152	72000	1.5031
0.1154	72100	1.5412
0.1155	72200	1.2971
0.1157	72300	1.0979
0.1158	72400	1.307
0.1160	72500	1.3418
0.1162	72600	1.7298
0.1163	72700	1.68
0.1165	72800	1.3106
0.1166	72900	1.0954
0.1168	73000	1.5994
0.1170	73100	1.5953
0.1171	73200	1.9498
0.1173	73300	0.9937
0.1174	73400	1.4753
0.1176	73500	1.417
0.1178	73600	1.596
0.1179	73700	1.8794
0.1181	73800	1.3118
0.1182	73900	1.732
0.1184	74000	1.4504
0.1186	74100	1.0878
0.1187	74200	1.2488
0.1189	74300	1.3887
0.1190	74400	1.2265
0.1192	74500	1.4668
0.1194	74600	1.6258
0.1195	74700	1.9551
0.1197	74800	1.1811
0.1198	74900	1.2119
0.1200	75000	1.4051
0.1202	75100	1.2587
0.1203	75200	1.4563
0.1205	75300	1.5581
0.1206	75400	1.5457
0.1208	75500	1.2675
0.1210	75600	1.0948
0.1211	75700	1.2045
0.1213	75800	1.5964
0.1214	75900	1.0517
0.1216	76000	1.2883
0.1218	76100	1.2276
0.1219	76200	1.2463
0.1221	76300	1.241
0.1222	76400	1.8648
0.1224	76500	1.4848
0.1226	76600	1.413
0.1227	76700	1.594
0.1229	76800	1.3682
0.1230	76900	1.159
0.1232	77000	1.4702
0.1234	77100	1.3251
0.1235	77200	1.0538
0.1237	77300	1.1708
0.1238	77400	1.2864
0.1240	77500	1.6501
0.1242	77600	1.0104
0.1243	77700	1.7969
0.1245	77800	1.0293
0.1246	77900	1.5593
0.1248	78000	0.9902
0.1250	78100	1.058
0.1251	78200	1.4039
0.1253	78300	1.008
0.1254	78400	1.4593
0.1256	78500	1.563
0.1258	78600	1.1569
0.1259	78700	1.3886
0.1261	78800	1.061
0.1262	78900	1.2085
0.1264	79000	1.8553
0.1266	79100	1.7144
0.1267	79200	1.2216
0.1269	79300	1.1646
0.1270	79400	1.7768
0.1272	79500	1.1314
0.1274	79600	1.2374
0.1275	79700	1.2681
0.1277	79800	1.2624
0.1278	79900	1.6775
0.1280	80000	1.3587
0.1282	80100	1.7402
0.1283	80200	1.5349
0.1285	80300	0.8546
0.1286	80400	1.3903
0.1288	80500	1.0712
0.1290	80600	1.6633
0.1291	80700	1.4125
0.1293	80800	0.6973
0.1294	80900	1.1729
0.1296	81000	1.2217
0.1298	81100	1.3184
0.1299	81200	1.2718
0.1301	81300	1.1913
0.1302	81400	1.4728
0.1304	81500	1.1221
0.1306	81600	1.235
0.1307	81700	1.3497
0.1309	81800	1.2361
0.1310	81900	2.0015
0.1312	82000	1.2259
0.1314	82100	0.9236
0.1315	82200	1.5339
0.1317	82300	1.2036
0.1318	82400	1.2631
0.1320	82500	1.0858
0.1322	82600	1.635
0.1323	82700	1.285
0.1325	82800	1.1209
0.1326	82900	1.4032
0.1328	83000	1.1279
0.1330	83100	1.5145
0.1331	83200	1.4923
0.1333	83300	0.9845
0.1334	83400	1.3847
0.1336	83500	1.0149
0.1338	83600	1.2644
0.1339	83700	1.2981
0.1341	83800	1.6903
0.1342	83900	1.2846
0.1344	84000	1.4647
0.1346	84100	1.1213
0.1347	84200	1.1379
0.1349	84300	1.2793
0.1350	84400	1.343
0.1352	84500	1.8342
0.1354	84600	1.0487
0.1355	84700	1.1531
0.1357	84800	0.8552
0.1358	84900	1.1422
0.1360	85000	1.0918
0.1362	85100	1.2873
0.1363	85200	1.547
0.1365	85300	1.5094
0.1366	85400	1.051
0.1368	85500	0.9952
0.1370	85600	1.1978
0.1371	85700	1.5221
0.1373	85800	1.3841
0.1374	85900	1.3999
0.1376	86000	1.5574
0.1378	86100	1.3267
0.1379	86200	1.358
0.1381	86300	1.5441
0.1382	86400	1.4124
0.1384	86500	0.8352
0.1386	86600	1.2549
0.1387	86700	1.4328
0.1389	86800	1.2577
0.1390	86900	1.4417
0.1392	87000	1.1927
0.1394	87100	1.4435
0.1395	87200	1.3579
0.1397	87300	1.3883
0.1398	87400	1.2645
0.1400	87500	1.1366
0.1402	87600	1.4566
0.1403	87700	1.447
0.1405	87800	1.0701
0.1406	87900	1.3449
0.1408	88000	1.4331
0.1410	88100	1.3965
0.1411	88200	1.347
0.1413	88300	1.0262
0.1414	88400	1.0787
0.1416	88500	1.3829
0.1418	88600	1.2001
0.1419	88700	1.2407
0.1421	88800	1.6291
0.1422	88900	1.1502
0.1424	89000	1.2155
0.1426	89100	1.3381
0.1427	89200	0.819
0.1429	89300	1.0402
0.1430	89400	1.1062
0.1432	89500	1.6693
0.1434	89600	1.1991
0.1435	89700	1.3535
0.1437	89800	1.6776
0.1438	89900	1.2221
0.1440	90000	1.0253
0.1442	90100	1.0469
0.1443	90200	1.2465
0.1445	90300	1.4068
0.1446	90400	1.5961
0.1448	90500	1.0579
0.1450	90600	0.941
0.1451	90700	1.1861
0.1453	90800	1.4697
0.1454	90900	0.6486
0.1456	91000	1.3865
0.1458	91100	1.1494
0.1459	91200	1.3623
0.1461	91300	1.2193
0.1462	91400	1.3003
0.1464	91500	1.2608
0.1466	91600	1.2544
0.1467	91700	1.332
0.1469	91800	1.3548
0.1470	91900	1.54
0.1472	92000	1.3125
0.1474	92100	0.897
0.1475	92200	1.1594
0.1477	92300	0.9194
0.1478	92400	1.2209
0.1480	92500	1.0027
0.1482	92600	1.4675
0.1483	92700	1.3982
0.1485	92800	0.8595
0.1486	92900	1.572
0.1488	93000	1.2832
0.1490	93100	1.2838
0.1491	93200	1.6535
0.1493	93300	1.5996
0.1494	93400	1.058
0.1496	93500	1.3316
0.1498	93600	0.8627
0.1499	93700	1.4411
0.1501	93800	0.9331
0.1502	93900	1.0032
0.1504	94000	1.2341
0.1506	94100	1.3369
0.1507	94200	1.2324
0.1509	94300	1.6952
0.1510	94400	1.2401
0.1512	94500	1.2998
0.1514	94600	1.1458
0.1515	94700	1.0211
0.1517	94800	0.9866
0.1518	94900	1.3636
0.1520	95000	1.1485
0.1522	95100	0.7671
0.1523	95200	1.0069
0.1525	95300	1.1276
0.1526	95400	1.4477
0.1528	95500	0.9887
0.1530	95600	1.065
0.1531	95700	0.982
0.1533	95800	1.1166
0.1534	95900	1.3949
0.1536	96000	1.4164
0.1538	96100	1.7997
0.1539	96200	1.3941
0.1541	96300	1.0592
0.1542	96400	1.1661
0.1544	96500	1.5968
0.1546	96600	1.2586
0.1547	96700	1.5164
0.1549	96800	1.5942
0.1550	96900	0.6635
0.1552	97000	1.3037
0.1554	97100	1.3557
0.1555	97200	1.0864
0.1557	97300	1.3139
0.1558	97400	0.7139
0.1560	97500	1.1084
0.1562	97600	1.2294
0.1563	97700	0.9581
0.1565	97800	1.2983
0.1566	97900	1.8281
0.1568	98000	1.2914
0.1570	98100	0.8656
0.1571	98200	1.3438
0.1573	98300	1.465
0.1574	98400	1.2253
0.1576	98500	1.3481
0.1578	98600	1.5131
0.1579	98700	1.4852
0.1581	98800	1.1317
0.1582	98900	1.0395
0.1584	99000	0.9256
0.1586	99100	0.9774
0.1587	99200	0.9756
0.1589	99300	1.4885
0.1590	99400	1.2373
0.1592	99500	1.3868
0.1594	99600	0.9238
0.1595	99700	1.0793
0.1597	99800	1.2405
0.1598	99900	1.2417
0.1600	100000	1.1264
0.1602	100100	1.3042
0.1603	100200	1.7169
0.1605	100300	1.0939
0.1606	100400	1.4
0.1608	100500	1.1289

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},
}