Yalexk/newsroom_embedding_model

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

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 retrieval.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: sentence-transformers/all-MiniLM-L6-v2
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity
• Supported Modality: Text

Model Sources

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

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
  (1): Pooling({'embedding_dimension': 384, 'pooling_mode': 'mean', '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 = [
    'guest post by katherine kelly lutton, principal and global head of litigation, fish & richardson pc at last week ’ s fortune most powerful women dinner in washington, i found myself sandwiched between cnn national political correspondent jessica yellin and jane roberts, former litigator and law firm leader and wife of chief justice john roberts. jessica and jane, meanwhile, were sitting between two mentees from haiti — two courageous women among 33 who are part of fortune ‘ s mentoring partnership with the u. s. state department. i ’ m a mentor. how can i not be? every april, fortune invites women who come to its most powerful women summit to mentor rising women leaders from emerging countries around the world. the program seems right for the time. we have globalization on all fronts including the globalization of “ communities. ” think about it. while social relationships and values and “ mentoring ” used to spring out of physically cohesive groups of people connecting according to commonalities ( beliefs about god, job types, organizations ), connecting this way too often meant a senior caucasian man taking a junior caucasian man “ under his wing. ” mentoring women leaders across the globe turns traditional concepts of community and mentoring on their head. i was inspired when i first saw this in action at the mpwomen summit in 2008. where do i sign up?! i did sign up — but i felt empowered to do more. what if i mentored with one other woman from silicon valley who would showcase her skills, experiences and contacts?. or what if i teamed up with two women or three … or 50? on behalf of all the women i knew, i signed up to “ community ” mentor. fast forward about nine months ( the birth of anything worthwhile takes about that long ), and “ our ” mentee, susan rammekwa, steps off the plane from her home country, south africa. susan is a highly religious woman who runs an ngo called tshepang ( “ have hope ” ) programme and an “ empowerment village ” for children whose parents have died from hiv / aids. for 200 homeless and parentless children ages three to 17, tshepang provides daily care, access to education, social skills and a balanced meal.',
    "Guest Post by Katherine Kelly Lutton, Principal and Global Head of Litigation, Fish & Richardson PC At last week's Fortune Most Powerful Women dinner in Washington, I found myself sandwiched between CNN National Political Correspondent Jessica Yellin\xa0and Jane Roberts, former litigator and law firm leader and wife of Chief Justice John Roberts. Jessica and Jane,…",
    'Massachusetts has its share of defense industry contractors, but none like this. Sterlingwear Boston peacoats for the US Navy -- 40,000 of them this year.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000,  0.6002,  0.0343],
#         [ 0.6002,  1.0000, -0.0063],
#         [ 0.0343, -0.0063,  1.0000]])

Training Details

Training Dataset

Unnamed Dataset

• Size: 2,082,630 training samples
• Columns: sentence_0 and sentence_1
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1
  type	string	string
  details	min: 4 tokens mean: 190.49 tokens max: 256 tokens	min: 5 tokens mean: 50.76 tokens max: 256 tokens

• Samples:

  sentence_0	sentence_1
  escalating its competition with other boston - area hospital chains, for - profit company steward health care system has again lured away a major doctors group from a rival, this time grabbing a large south shore practice from partners healthcare. deep - pocketed newcomer steward said yesterday that compass medical will join its network, a move that could shake up patient and provider relationships in communities south of boston. compass medical includes 90 doctors in eight offices between braintree and taunton, and over time, doctors there probably will refer more of their thousands of patients to nearby steward - owned community hospitals for care, including quincy medical center, good samaritan medical center in brockton, and morton hospital in taunton. the change is a loss for partners, a powerful provider network that includes massachusetts general and brigham and women ’ s hospitals, which has been affiliated with compass for 16 years. steward ’ s partnership with compass comes a...	Escalating its competition with other Boston-area hospital chains, for-profit company Steward Health Care System has lured away another major doctors group from a rival, this time grabbing a large South Shore practice from Partners HealthCare. Deep-pocketed newcomer Steward said yesterday that Compass Medical will join its network - a move that could shake up patient and provider relationships in communities south of Boston.
  04 / 09 / 2015 at 07 : 55 pm edt is ( finally ) getting his own reality show – and who better to produce the docuseries than the guys behind frontman ' s move from london to los angeles, according to george, 53, announced the show by proclaiming, " if marge simpson met dolly parton and went dancing with ziggy stardust, it wouldnat come close to what youall see. " and if you had any questions as to why the former pop star has suddenly decided to try his hand at television, he ' s got the answers : " why now – why not? why me – who else? a for anyone who missed out on the ' 80s, boy george had a string of hits with his band, the culture club – including classics like " karma chameleon, " " do you really want to hurt me, " and " i ' ll tumble 4 ya. " the british singer ' s androgynous persona was considered quite shocking at the time. aboy george is a musical and cultural icon, and itas about time someone captured his story, " said gil goldschein, chairman and ceo of bmp. " we are experts...	The show will chronicle the Culture Club frontman's move from London to Los Angeles
  color in my hair because my grandson says i look younger. ’ “ some like a lot of teasing and the old - style final net hairspray. a lot of ladies feel like they are going bald, but we have all kinds of tricks up on our sleeve, like a fiber product that fills in spots. the memory issues can be a challenge ; we need to have a receptionist because often people forget their appointment or come back in after they were just here yesterday. those with alzheimer ’ s are afraid of the water, and we can ’ t lay their	You’re never too old to want to look beautiful. Ask hair salon director Bernice Cunningham at Brooksby Village in Peabody.

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false,
      "directions": [
          "query_to_doc"
      ],
      "partition_mode": "joint",
      "hardness_mode": null,
      "hardness_strength": 0.0
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 16
• fp16: True
• per_device_eval_batch_size: 16
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• per_device_train_batch_size: 16
• num_train_epochs: 3
• max_steps: -1
• learning_rate: 5e-05
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• warmup_steps: 0
• optim: adamw_torch_fused
• optim_args: None
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• optim_target_modules: None
• gradient_accumulation_steps: 1
• average_tokens_across_devices: True
• max_grad_norm: 1
• label_smoothing_factor: 0.0
• bf16: False
• fp16: True
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• use_liger_kernel: False
• liger_kernel_config: None
• use_cache: False
• neftune_noise_alpha: None
• torch_empty_cache_steps: None
• auto_find_batch_size: False
• log_on_each_node: True
• logging_nan_inf_filter: True
• include_num_input_tokens_seen: no
• log_level: passive
• log_level_replica: warning
• disable_tqdm: False
• project: huggingface
• trackio_space_id: trackio
• eval_strategy: no
• per_device_eval_batch_size: 16
• prediction_loss_only: True
• eval_on_start: False
• eval_do_concat_batches: True
• eval_use_gather_object: False
• eval_accumulation_steps: None
• include_for_metrics: []
• batch_eval_metrics: False
• save_only_model: False
• save_on_each_node: False
• enable_jit_checkpoint: False
• push_to_hub: False
• hub_private_repo: None
• hub_model_id: None
• hub_strategy: every_save
• hub_always_push: False
• hub_revision: None
• load_best_model_at_end: False
• ignore_data_skip: False
• restore_callback_states_from_checkpoint: False
• full_determinism: False
• seed: 42
• data_seed: None
• use_cpu: False
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• parallelism_config: None
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• dataloader_prefetch_factor: None
• remove_unused_columns: True
• label_names: None
• train_sampling_strategy: random
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• ddp_backend: None
• ddp_timeout: 1800
• fsdp: []
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• deepspeed: None
• debug: []
• skip_memory_metrics: True
• do_predict: False
• resume_from_checkpoint: None
• warmup_ratio: None
• local_rank: -1
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Click to expand

Epoch	Step	Training Loss
0.0038	500	0.3678
0.0077	1000	0.3640
0.0115	1500	0.3275
0.0154	2000	0.3446
0.0192	2500	0.3159
0.0230	3000	0.3296
0.0269	3500	0.3178
0.0307	4000	0.3090
0.0346	4500	0.2909
0.0384	5000	0.2802
0.0423	5500	0.2910
0.0461	6000	0.2904
0.0499	6500	0.3037
0.0538	7000	0.2768
0.0576	7500	0.2607
0.0615	8000	0.2610
0.0653	8500	0.2502
0.0691	9000	0.2604
0.0730	9500	0.2533
0.0768	10000	0.2673
0.0807	10500	0.2512
0.0845	11000	0.2726
0.0883	11500	0.2541
0.0922	12000	0.2560
0.0960	12500	0.2386
0.0999	13000	0.2539
0.1037	13500	0.2382
0.1076	14000	0.2401
0.1114	14500	0.2419
0.1152	15000	0.2364
0.1191	15500	0.2439
0.1229	16000	0.2408
0.1268	16500	0.2367
0.1306	17000	0.2319
0.1344	17500	0.2282
0.1383	18000	0.2385
0.1421	18500	0.2369
0.1460	19000	0.2405
0.1498	19500	0.2156
0.1537	20000	0.2264
0.1575	20500	0.2123
0.1613	21000	0.2254
0.1652	21500	0.2270
0.1690	22000	0.2209
0.1729	22500	0.2189
0.1767	23000	0.2110
0.1805	23500	0.2122
0.1844	24000	0.2136
0.1882	24500	0.2201
0.1921	25000	0.2138
0.1959	25500	0.2147
0.1997	26000	0.2239
0.2036	26500	0.2175
0.2074	27000	0.2207
0.2113	27500	0.2087
0.2151	28000	0.2137
0.2190	28500	0.2054
0.2228	29000	0.2142
0.2266	29500	0.2134
0.2305	30000	0.2205
0.2343	30500	0.2072
0.2382	31000	0.2092
0.2420	31500	0.2056
0.2458	32000	0.2231
0.2497	32500	0.2087
0.2535	33000	0.2088
0.2574	33500	0.2093
0.2612	34000	0.2251
0.2650	34500	0.2150
0.2689	35000	0.2061
0.2727	35500	0.2083
0.2766	36000	0.2109
0.2804	36500	0.2107
0.2843	37000	0.2128
0.2881	37500	0.2038
0.2919	38000	0.2161
0.2958	38500	0.2009
0.2996	39000	0.2192
0.3035	39500	0.2032
0.3073	40000	0.2059
0.3111	40500	0.1981
0.3150	41000	0.2059
0.3188	41500	0.2035
0.3227	42000	0.2133
0.3265	42500	0.2007
0.3303	43000	0.1957
0.3342	43500	0.2006
0.3380	44000	0.2088
0.3419	44500	0.2117
0.3457	45000	0.1942
0.3496	45500	0.1930
0.3534	46000	0.2150
0.3572	46500	0.2007
0.3611	47000	0.2027
0.3649	47500	0.1995
0.3688	48000	0.2076
0.3726	48500	0.1971
0.3764	49000	0.1997
0.3803	49500	0.2058
0.3841	50000	0.2058
0.3880	50500	0.1983
0.3918	51000	0.1988
0.3957	51500	0.1814
0.3995	52000	0.1937
0.4033	52500	0.1846
0.4072	53000	0.1969
0.4110	53500	0.2025
0.4149	54000	0.1952
0.4187	54500	0.1998
0.4225	55000	0.1868
0.4264	55500	0.1907
0.4302	56000	0.1876
0.4341	56500	0.1841
0.4379	57000	0.1896
0.4417	57500	0.1811
0.4456	58000	0.1892
0.4494	58500	0.1966
0.4533	59000	0.1887
0.4571	59500	0.1907
0.4610	60000	0.1970
0.4648	60500	0.1729
0.4686	61000	0.2036
0.4725	61500	0.1834
0.4763	62000	0.1984
0.4802	62500	0.1730
0.4840	63000	0.1917
0.4878	63500	0.1889
0.4917	64000	0.1866
0.4955	64500	0.2027
0.4994	65000	0.1960
0.5032	65500	0.1866
0.5070	66000	0.1914
0.5109	66500	0.2108
0.5147	67000	0.1963
0.5186	67500	0.2001
0.5224	68000	0.1829
0.5263	68500	0.1808
0.5301	69000	0.1778
0.5339	69500	0.1887
0.5378	70000	0.1893
0.5416	70500	0.1784
0.5455	71000	0.1962
0.5493	71500	0.1884
0.5531	72000	0.1951
0.5570	72500	0.1785
0.5608	73000	0.2019
0.5647	73500	0.1841
0.5685	74000	0.1755
0.5724	74500	0.1708
0.5762	75000	0.1815
0.5800	75500	0.1855
0.5839	76000	0.1792
0.5877	76500	0.1783
0.5916	77000	0.1897
0.5954	77500	0.1778
0.5992	78000	0.1819
0.6031	78500	0.1726
0.6069	79000	0.1726
0.6108	79500	0.1799
0.6146	80000	0.1790
0.6184	80500	0.1682
0.6223	81000	0.1728
0.6261	81500	0.1789
0.6300	82000	0.1784
0.6338	82500	0.1890
0.6377	83000	0.1803
0.6415	83500	0.1727
0.6453	84000	0.1696
0.6492	84500	0.1715
0.6530	85000	0.1696
0.6569	85500	0.1811
0.6607	86000	0.1695
0.6645	86500	0.1872
0.6684	87000	0.1797
0.6722	87500	0.1774
0.6761	88000	0.1758
0.6799	88500	0.1764
0.6837	89000	0.1648
0.6876	89500	0.1629
0.6914	90000	0.1742
0.6953	90500	0.1834
0.6991	91000	0.1752
0.7030	91500	0.1609
0.7068	92000	0.1793
0.7106	92500	0.1716
0.7145	93000	0.1679
0.7183	93500	0.1695
0.7222	94000	0.1780
0.7260	94500	0.1689
0.7298	95000	0.1649
0.7337	95500	0.1699
0.7375	96000	0.1674
0.7414	96500	0.1582
0.7452	97000	0.1968
0.7490	97500	0.1755
0.7529	98000	0.1646
0.7567	98500	0.1567
0.7606	99000	0.1764
0.7644	99500	0.1711
0.7683	100000	0.1648
0.7721	100500	0.1568
0.7759	101000	0.1770
0.7798	101500	0.1592
0.7836	102000	0.1607
0.7875	102500	0.1591
0.7913	103000	0.1833
0.7951	103500	0.1623
0.7990	104000	0.1750
0.8028	104500	0.1642
0.8067	105000	0.1561
0.8105	105500	0.1680
0.8144	106000	0.1745
0.8182	106500	0.1620
0.8220	107000	0.1675
0.8259	107500	0.1566
0.8297	108000	0.1706
0.8336	108500	0.1641
0.8374	109000	0.1578
0.8412	109500	0.1565
0.8451	110000	0.1605
0.8489	110500	0.1732
0.8528	111000	0.1599
0.8566	111500	0.1577
0.8604	112000	0.1571
0.8643	112500	0.1585
0.8681	113000	0.1687
0.8720	113500	0.1535
0.8758	114000	0.1732
0.8797	114500	0.1692
0.8835	115000	0.1539
0.8873	115500	0.1680
0.8912	116000	0.1696
0.8950	116500	0.1518
0.8989	117000	0.1565
0.9027	117500	0.1495
0.9065	118000	0.1644
0.9104	118500	0.1585
0.9142	119000	0.1611
0.9181	119500	0.1545
0.9219	120000	0.1694
0.9257	120500	0.1594
0.9296	121000	0.1629
0.9334	121500	0.1552
0.9373	122000	0.1555
0.9411	122500	0.1642
0.9450	123000	0.1420
0.9488	123500	0.1608
0.9526	124000	0.1551
0.9565	124500	0.1494
0.9603	125000	0.1650
0.9642	125500	0.1562
0.9680	126000	0.1588
0.9718	126500	0.1534
0.9757	127000	0.1529
0.9795	127500	0.1678
0.9834	128000	0.1717
0.9872	128500	0.1547
0.9910	129000	0.1582
0.9949	129500	0.1475
0.9987	130000	0.1625
1.0026	130500	0.1454
1.0064	131000	0.1413
1.0103	131500	0.1417
1.0141	132000	0.1497
1.0179	132500	0.1471
1.0218	133000	0.1425
1.0256	133500	0.1446
1.0295	134000	0.1375
1.0333	134500	0.1377
1.0371	135000	0.1250
1.0410	135500	0.1359
1.0448	136000	0.1316
1.0487	136500	0.1274
1.0525	137000	0.1426
1.0564	137500	0.1261
1.0602	138000	0.1446
1.0640	138500	0.1313
1.0679	139000	0.1405
1.0717	139500	0.1359
1.0756	140000	0.1331
1.0794	140500	0.1282
1.0832	141000	0.1382
1.0871	141500	0.1286
1.0909	142000	0.1316
1.0948	142500	0.1320
1.0986	143000	0.1306
1.1024	143500	0.1449
1.1063	144000	0.1205
1.1101	144500	0.1350
1.1140	145000	0.1371
1.1178	145500	0.1224
1.1217	146000	0.1309
1.1255	146500	0.1356
1.1293	147000	0.1202
1.1332	147500	0.1351
1.1370	148000	0.1337
1.1409	148500	0.1321
1.1447	149000	0.1273
1.1485	149500	0.1222
1.1524	150000	0.1362
1.1562	150500	0.1395
1.1601	151000	0.1403
1.1639	151500	0.1377
1.1677	152000	0.1297
1.1716	152500	0.1366
1.1754	153000	0.1304
1.1793	153500	0.1261
1.1831	154000	0.1298
1.1870	154500	0.1308
1.1908	155000	0.1410
1.1946	155500	0.1336
1.1985	156000	0.1269
1.2023	156500	0.1327
1.2062	157000	0.1272
1.2100	157500	0.1285
1.2138	158000	0.1281
1.2177	158500	0.1378
1.2215	159000	0.1360
1.2254	159500	0.1270
1.2292	160000	0.1285
1.2331	160500	0.1367
1.2369	161000	0.1327
1.2407	161500	0.1194
1.2446	162000	0.1220
1.2484	162500	0.1274
1.2523	163000	0.1278
1.2561	163500	0.1451
1.2599	164000	0.1319
1.2638	164500	0.1313
1.2676	165000	0.1293
1.2715	165500	0.1360
1.2753	166000	0.1283
1.2791	166500	0.1347
1.2830	167000	0.1344
1.2868	167500	0.1249
1.2907	168000	0.1250
1.2945	168500	0.1295
1.2984	169000	0.1307
1.3022	169500	0.1373
1.3060	170000	0.1367
1.3099	170500	0.1259
1.3137	171000	0.1366
1.3176	171500	0.1347
1.3214	172000	0.1297
1.3252	172500	0.1260
1.3291	173000	0.1299
1.3329	173500	0.1377
1.3368	174000	0.1322
1.3406	174500	0.1231
1.3444	175000	0.1380
1.3483	175500	0.1304
1.3521	176000	0.1201
1.3560	176500	0.1201
1.3598	177000	0.1268
1.3637	177500	0.1143
1.3675	178000	0.1314
1.3713	178500	0.1251
1.3752	179000	0.1266
1.3790	179500	0.1292
1.3829	180000	0.1210
1.3867	180500	0.1250
1.3905	181000	0.1262
1.3944	181500	0.1237
1.3982	182000	0.1436
1.4021	182500	0.1252
1.4059	183000	0.1275
1.4097	183500	0.1251
1.4136	184000	0.1174
1.4174	184500	0.1294
1.4213	185000	0.1262
1.4251	185500	0.1246
1.4290	186000	0.1183
1.4328	186500	0.1160
1.4366	187000	0.1263
1.4405	187500	0.1176
1.4443	188000	0.1160
1.4482	188500	0.1154
1.4520	189000	0.1341
1.4558	189500	0.1290
1.4597	190000	0.1479
1.4635	190500	0.1308
1.4674	191000	0.1200
1.4712	191500	0.1250
1.4751	192000	0.1221
1.4789	192500	0.1155
1.4827	193000	0.1118
1.4866	193500	0.1279
1.4904	194000	0.1404
1.4943	194500	0.1291
1.4981	195000	0.1179
1.5019	195500	0.1152
1.5058	196000	0.1193
1.5096	196500	0.1359
1.5135	197000	0.1233
1.5173	197500	0.1253
1.5211	198000	0.1220
1.5250	198500	0.1139
1.5288	199000	0.1302
1.5327	199500	0.1302
1.5365	200000	0.1172
1.5404	200500	0.1318
1.5442	201000	0.1265
1.5480	201500	0.1250
1.5519	202000	0.1234
1.5557	202500	0.1313
1.5596	203000	0.1339
1.5634	203500	0.1186
1.5672	204000	0.1236
1.5711	204500	0.1264
1.5749	205000	0.1230
1.5788	205500	0.1262
1.5826	206000	0.1321
1.5864	206500	0.1193
1.5903	207000	0.1250
1.5941	207500	0.1216
1.5980	208000	0.1155
1.6018	208500	0.1267
1.6057	209000	0.1144
1.6095	209500	0.1304
1.6133	210000	0.1292
1.6172	210500	0.1201
1.6210	211000	0.1282
1.6249	211500	0.1235
1.6287	212000	0.1310
1.6325	212500	0.1224
1.6364	213000	0.1196
1.6402	213500	0.1288
1.6441	214000	0.1268
1.6479	214500	0.1072
1.6517	215000	0.1169
1.6556	215500	0.1303
1.6594	216000	0.1281
1.6633	216500	0.1157
1.6671	217000	0.1223
1.6710	217500	0.1339
1.6748	218000	0.1162
1.6786	218500	0.1262
1.6825	219000	0.1211
1.6863	219500	0.1308
1.6902	220000	0.1220
1.6940	220500	0.1154
1.6978	221000	0.1217
1.7017	221500	0.1190
1.7055	222000	0.1211
1.7094	222500	0.1195
1.7132	223000	0.1242
1.7171	223500	0.1177
1.7209	224000	0.1156
1.7247	224500	0.1193
1.7286	225000	0.1129
1.7324	225500	0.1217
1.7363	226000	0.1206
1.7401	226500	0.1286
1.7439	227000	0.1266
1.7478	227500	0.1188
1.7516	228000	0.1152
1.7555	228500	0.1204
1.7593	229000	0.1124
1.7631	229500	0.1231
1.7670	230000	0.1114
1.7708	230500	0.1201
1.7747	231000	0.1101
1.7785	231500	0.1131
1.7824	232000	0.1146
1.7862	232500	0.1224
1.7900	233000	0.1224
1.7939	233500	0.1254
1.7977	234000	0.1137
1.8016	234500	0.1169
1.8054	235000	0.1218
1.8092	235500	0.1258
1.8131	236000	0.1172
1.8169	236500	0.1194
1.8208	237000	0.1192
1.8246	237500	0.1296
1.8284	238000	0.1170
1.8323	238500	0.1124
1.8361	239000	0.1242
1.8400	239500	0.1238
1.8438	240000	0.1225
1.8477	240500	0.1185
1.8515	241000	0.1074
1.8553	241500	0.1262
1.8592	242000	0.1150
1.8630	242500	0.1198
1.8669	243000	0.1236
1.8707	243500	0.1070
1.8745	244000	0.1142
1.8784	244500	0.1184
1.8822	245000	0.1101
1.8861	245500	0.1120
1.8899	246000	0.1269
1.8938	246500	0.1191
1.8976	247000	0.1090
1.9014	247500	0.1158
1.9053	248000	0.1166
1.9091	248500	0.1188
1.9130	249000	0.1300
1.9168	249500	0.1181
1.9206	250000	0.1175
1.9245	250500	0.1232
1.9283	251000	0.1200
1.9322	251500	0.1224
1.9360	252000	0.1186
1.9398	252500	0.1117
1.9437	253000	0.1158
1.9475	253500	0.1167
1.9514	254000	0.1148
1.9552	254500	0.1086
1.9591	255000	0.1154
1.9629	255500	0.1194
1.9667	256000	0.1229
1.9706	256500	0.1180
1.9744	257000	0.1159
1.9783	257500	0.1081
1.9821	258000	0.1005
1.9859	258500	0.1196
1.9898	259000	0.1242
1.9936	259500	0.1101
1.9975	260000	0.1002
2.0013	260500	0.1138
2.0051	261000	0.1023
2.0090	261500	0.0971
2.0128	262000	0.0920
2.0167	262500	0.0986
2.0205	263000	0.1022
2.0244	263500	0.0979
2.0282	264000	0.1019
2.0320	264500	0.0899
2.0359	265000	0.0980
2.0397	265500	0.1036
2.0436	266000	0.0928
2.0474	266500	0.1021
2.0512	267000	0.1103
2.0551	267500	0.0971
2.0589	268000	0.1035
2.0628	268500	0.0952
2.0666	269000	0.1090
2.0704	269500	0.1020
2.0743	270000	0.1010
2.0781	270500	0.0901
2.0820	271000	0.0963
2.0858	271500	0.0987
2.0897	272000	0.1016
2.0935	272500	0.1022
2.0973	273000	0.1126
2.1012	273500	0.0874
2.1050	274000	0.1013
2.1089	274500	0.1060
2.1127	275000	0.0886
2.1165	275500	0.0974
2.1204	276000	0.0911
2.1242	276500	0.0993
2.1281	277000	0.1058
2.1319	277500	0.0938
2.1358	278000	0.1012
2.1396	278500	0.0948
2.1434	279000	0.1033
2.1473	279500	0.1011
2.1511	280000	0.0927
2.1550	280500	0.1080
2.1588	281000	0.1002
2.1626	281500	0.0887
2.1665	282000	0.0993
2.1703	282500	0.1040
2.1742	283000	0.0904
2.1780	283500	0.0993
2.1818	284000	0.1019
2.1857	284500	0.0947
2.1895	285000	0.0957
2.1934	285500	0.1036
2.1972	286000	0.0927
2.2011	286500	0.0879
2.2049	287000	0.1056
2.2087	287500	0.0994
2.2126	288000	0.0929
2.2164	288500	0.0982
2.2203	289000	0.0974
2.2241	289500	0.1047
2.2279	290000	0.1080
2.2318	290500	0.1028
2.2356	291000	0.1000
2.2395	291500	0.0921
2.2433	292000	0.0989
2.2471	292500	0.0923
2.2510	293000	0.0830
2.2548	293500	0.0972
2.2587	294000	0.0971
2.2625	294500	0.0918
2.2664	295000	0.0820
2.2702	295500	0.0886
2.2740	296000	0.0914
2.2779	296500	0.0941
2.2817	297000	0.0874
2.2856	297500	0.0973
2.2894	298000	0.0942
2.2932	298500	0.0964
2.2971	299000	0.0953
2.3009	299500	0.0880
2.3048	300000	0.0967
2.3086	300500	0.0997
2.3124	301000	0.0978
2.3163	301500	0.0884
2.3201	302000	0.0961
2.3240	302500	0.0982
2.3278	303000	0.0868
2.3317	303500	0.0903
2.3355	304000	0.0987
2.3393	304500	0.0978
2.3432	305000	0.0891
2.3470	305500	0.0998
2.3509	306000	0.0898
2.3547	306500	0.0943
2.3585	307000	0.0889
2.3624	307500	0.0986
2.3662	308000	0.1001
2.3701	308500	0.1002
2.3739	309000	0.0942
2.3778	309500	0.0928
2.3816	310000	0.0934
2.3854	310500	0.0978
2.3893	311000	0.1021
2.3931	311500	0.0930
2.3970	312000	0.1008
2.4008	312500	0.1011
2.4046	313000	0.0936
2.4085	313500	0.0923
2.4123	314000	0.0888
2.4162	314500	0.1005
2.4200	315000	0.0956
2.4238	315500	0.1016
2.4277	316000	0.0962
2.4315	316500	0.0903
2.4354	317000	0.0906
2.4392	317500	0.1001
2.4431	318000	0.0990
2.4469	318500	0.0908
2.4507	319000	0.0912
2.4546	319500	0.0900
2.4584	320000	0.0896
2.4623	320500	0.0963
2.4661	321000	0.0955
2.4699	321500	0.0827
2.4738	322000	0.0899
2.4776	322500	0.0879
2.4815	323000	0.0967
2.4853	323500	0.0947
2.4891	324000	0.0923
2.4930	324500	0.0905
2.4968	325000	0.0998
2.5007	325500	0.0882
2.5045	326000	0.1035
2.5084	326500	0.0995
2.5122	327000	0.0955
2.5160	327500	0.0852
2.5199	328000	0.0949
2.5237	328500	0.0960
2.5276	329000	0.0896
2.5314	329500	0.0915
2.5352	330000	0.0935
2.5391	330500	0.1006
2.5429	331000	0.1015
2.5468	331500	0.0907
2.5506	332000	0.1057
2.5545	332500	0.0989
2.5583	333000	0.0932
2.5621	333500	0.0936
2.5660	334000	0.1009
2.5698	334500	0.0922
2.5737	335000	0.0992
2.5775	335500	0.0981
2.5813	336000	0.0929
2.5852	336500	0.0884
2.5890	337000	0.0984
2.5929	337500	0.0939
2.5967	338000	0.0950
2.6005	338500	0.1009
2.6044	339000	0.1006
2.6082	339500	0.0957
2.6121	340000	0.0857
2.6159	340500	0.0875
2.6198	341000	0.0908
2.6236	341500	0.0917
2.6274	342000	0.1013
2.6313	342500	0.0885
2.6351	343000	0.0911
2.6390	343500	0.0940
2.6428	344000	0.0902
2.6466	344500	0.0961
2.6505	345000	0.0949
2.6543	345500	0.0962
2.6582	346000	0.1051
2.6620	346500	0.0843
2.6658	347000	0.0973
2.6697	347500	0.0900
2.6735	348000	0.0919
2.6774	348500	0.0949
2.6812	349000	0.0915
2.6851	349500	0.0948
2.6889	350000	0.0884
2.6927	350500	0.0991
2.6966	351000	0.0888
2.7004	351500	0.0947
2.7043	352000	0.0853
2.7081	352500	0.0972
2.7119	353000	0.0847
2.7158	353500	0.0940
2.7196	354000	0.0903
2.7235	354500	0.0808
2.7273	355000	0.0898
2.7311	355500	0.0894
2.7350	356000	0.1025
2.7388	356500	0.0806
2.7427	357000	0.0933
2.7465	357500	0.0949
2.7504	358000	0.0948
2.7542	358500	0.0941
2.7580	359000	0.0916
2.7619	359500	0.1019
2.7657	360000	0.0894
2.7696	360500	0.0971
2.7734	361000	0.0911
2.7772	361500	0.0888
2.7811	362000	0.0863
2.7849	362500	0.0882
2.7888	363000	0.0929
2.7926	363500	0.0883
2.7965	364000	0.0818
2.8003	364500	0.0955
2.8041	365000	0.0946
2.8080	365500	0.0891
2.8118	366000	0.0872
2.8157	366500	0.0896
2.8195	367000	0.0921
2.8233	367500	0.0898
2.8272	368000	0.0979
2.8310	368500	0.0952
2.8349	369000	0.0940
2.8387	369500	0.0930
2.8425	370000	0.0969
2.8464	370500	0.0881
2.8502	371000	0.1006
2.8541	371500	0.0925
2.8579	372000	0.0998
2.8618	372500	0.0899
2.8656	373000	0.0900
2.8694	373500	0.0969
2.8733	374000	0.0899
2.8771	374500	0.0872
2.8810	375000	0.0937
2.8848	375500	0.0921
2.8886	376000	0.0892
2.8925	376500	0.0910
2.8963	377000	0.0921
2.9002	377500	0.0915
2.9040	378000	0.1008
2.9078	378500	0.0832
2.9117	379000	0.0924
2.9155	379500	0.0874
2.9194	380000	0.0819
2.9232	380500	0.0890
2.9271	381000	0.0824
2.9309	381500	0.0946
2.9347	382000	0.0878
2.9386	382500	0.0855
2.9424	383000	0.0910
2.9463	383500	0.0927
2.9501	384000	0.0891
2.9539	384500	0.0948
2.9578	385000	0.0875
2.9616	385500	0.0918
2.9655	386000	0.0982
2.9693	386500	0.1000
2.9731	387000	0.0915
2.9770	387500	0.0900
2.9808	388000	0.0842
2.9847	388500	0.0910
2.9885	389000	0.0906
2.9924	389500	0.0855
2.9962	390000	0.0895

Training Time

• Training: 8.2 hours

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 5.4.0
• Transformers: 5.5.3
• PyTorch: 2.11.0+cu128
• Accelerate: 1.13.0
• Datasets: 4.8.4
• Tokenizers: 0.22.2

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",
}

MultipleNegativesRankingLoss

@misc{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}