CrossEncoder based on cross-encoder/ms-marco-MiniLM-L6-v2

This is a Cross Encoder model finetuned from cross-encoder/ms-marco-MiniLM-L6-v2 using the sentence-transformers library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.

Model Details

Model Description

Model Type: Cross Encoder
Base model: cross-encoder/ms-marco-MiniLM-L6-v2
Maximum Sequence Length: 512 tokens
Number of Output Labels: 1 label
Supported Modality: Text

Model Sources

Documentation: Sentence Transformers Documentation
Documentation: Cross Encoder Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Cross Encoders on Hugging Face

Full Model Architecture

CrossEncoder(
  (0): Transformer({'transformer_task': 'sequence-classification', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'logits'}}, 'module_output_name': 'scores', 'architecture': 'BertForSequenceClassification'})
)

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 CrossEncoder

# Download from the 🤗 Hub
model = CrossEncoder("jmroth/nlp-reranker-finetuned")
# Get scores for pairs of inputs
pairs = [
    ['Not only is there no scientific evidence that CO2 is a pollutant, higher CO2 concentrations actually help ecosystems support more plant and animal life.', 'Plants can grow as much as 50 percent faster in concentrations of 1,000 ppm CO 2 when compared with ambient conditions, though this assumes no change in climate and no limitation on other nutrients.'],
    ['Not only is there no scientific evidence that CO2 is a pollutant, higher CO2 concentrations actually help ecosystems support more plant and animal life.', 'Higher carbon dioxide concentrations will favourably affect plant growth and demand for water.'],
    ['Not only is there no scientific evidence that CO2 is a pollutant, higher CO2 concentrations actually help ecosystems support more plant and animal life.', 'At very high concentrations (100 times atmospheric concentration, or greater), carbon dioxide can be toxic to animal life, so raising the concentration to 10,000 ppm (1%) or higher for several hours will eliminate pests such as whiteflies and spider mites in a greenhouse.'],
    ['Not only is there no scientific evidence that CO2 is a pollutant, higher CO2 concentrations actually help ecosystems support more plant and animal life.', 'Use of fertilizers are beneficial in providing nutrients to plants although they have some negative environmental effects.'],
    ['Not only is there no scientific evidence that CO2 is a pollutant, higher CO2 concentrations actually help ecosystems support more plant and animal life.', 'Studies have shown that higher CO2 levels lead to reduced plant uptake of nitrogen (and a smaller number showing the same for trace elements such as zinc) resulting in crops with lower nutritional value.'],
]
scores = model.predict(pairs)
print(scores)
# [0.32   0.2035 0.4209 0.1389 0.4395]

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'Not only is there no scientific evidence that CO2 is a pollutant, higher CO2 concentrations actually help ecosystems support more plant and animal life.',
    [
        'Plants can grow as much as 50 percent faster in concentrations of 1,000 ppm CO 2 when compared with ambient conditions, though this assumes no change in climate and no limitation on other nutrients.',
        'Higher carbon dioxide concentrations will favourably affect plant growth and demand for water.',
        'At very high concentrations (100 times atmospheric concentration, or greater), carbon dioxide can be toxic to animal life, so raising the concentration to 10,000 ppm (1%) or higher for several hours will eliminate pests such as whiteflies and spider mites in a greenhouse.',
        'Use of fertilizers are beneficial in providing nutrients to plants although they have some negative environmental effects.',
        'Studies have shown that higher CO2 levels lead to reduced plant uptake of nitrogen (and a smaller number showing the same for trace elements such as zinc) resulting in crops with lower nutritional value.',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Training Details

Training Dataset

Unnamed Dataset

Size: 18,858 training samples
Columns: sentence1, sentence2, and label
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label
type string string float
details
min: 9 tokens
mean: 26.48 tokens
max: 54 tokens

min: 4 tokens
mean: 33.8 tokens
max: 475 tokens

min: 0.0
mean: 0.24
max: 1.0

	sentence1	sentence2	label
type	string	string	float
details	min: 9 tokens mean: 26.48 tokens max: 54 tokens	min: 4 tokens mean: 33.8 tokens max: 475 tokens	min: 0.0 mean: 0.24 max: 1.0

Samples:

sentence1	sentence2	label
`Not only is there no scientific evidence that CO2 is a pollutant, higher CO2 concentrations actually help ecosystems support more plant and animal life.`	`Plants can grow as much as 50 percent faster in concentrations of 1,000 ppm CO 2 when compared with ambient conditions, though this assumes no change in climate and no limitation on other nutrients.`	`1.0`
`Not only is there no scientific evidence that CO2 is a pollutant, higher CO2 concentrations actually help ecosystems support more plant and animal life.`	`Higher carbon dioxide concentrations will favourably affect plant growth and demand for water.`	`1.0`
`Not only is there no scientific evidence that CO2 is a pollutant, higher CO2 concentrations actually help ecosystems support more plant and animal life.`	`At very high concentrations (100 times atmospheric concentration, or greater), carbon dioxide can be toxic to animal life, so raising the concentration to 10,000 ppm (1%) or higher for several hours will eliminate pests such as whiteflies and spider mites in a greenhouse.`	`1.0`

Loss: BinaryCrossEntropyLoss with these parameters:

{
    "activation_fn": "torch.nn.modules.linear.Identity",
    "pos_weight": null
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
learning_rate: 1e-06
weight_decay: 0.01
num_train_epochs: 5
warmup_steps: 0.1
fp16: True

All Hyperparameters

Click to expand

do_predict: False
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 8
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 1e-06
weight_decay: 0.01
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 5
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_ratio: None
warmup_steps: 0.1
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
enable_jit_checkpoint: False
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
use_cpu: False
seed: 42
data_seed: None
bf16: False
fp16: True
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: -1
ddp_backend: None
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': 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
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch_fused
optim_args: None
group_by_length: False
length_column_name: length
project: huggingface
trackio_space_id: trackio
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
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
hub_revision: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_for_metrics: []
eval_do_concat_batches: True
auto_find_batch_size: False
full_determinism: False
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_num_input_tokens_seen: no
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: True
use_cache: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Click to expand

Epoch	Step	Training Loss
0.0085	10	1.0242
0.0170	20	1.3311
0.0254	30	1.2281
0.0339	40	1.1490
0.0424	50	1.3295
0.0509	60	1.1771
0.0594	70	1.2986
0.0679	80	1.1451
0.0763	90	0.9617
0.0848	100	0.9573
0.0933	110	1.1310
0.1018	120	1.1037
0.1103	130	0.8294
0.1187	140	1.2412
0.1272	150	1.5379
0.1357	160	0.8937
0.1442	170	1.0990
0.1527	180	1.2441
0.1612	190	0.9481
0.1696	200	1.0538
0.1781	210	1.2861
0.1866	220	1.1759
0.1951	230	1.0645
0.2036	240	1.3782
0.2120	250	1.1335
0.2205	260	1.1956
0.2290	270	1.2743
0.2375	280	1.3976
0.2460	290	1.2965
0.2545	300	1.3064
0.2629	310	1.4721
0.2714	320	1.0270
0.2799	330	0.8853
0.2884	340	1.1295
0.2969	350	1.0856
0.3053	360	1.0361
0.3138	370	0.9704
0.3223	380	0.9981
0.3308	390	1.1587
0.3393	400	1.0416
0.3478	410	1.0385
0.3562	420	0.9801
0.3647	430	1.0559
0.3732	440	0.9274
0.3817	450	0.8217
0.3902	460	0.8266
0.3986	470	1.0941
0.4071	480	0.8873
0.4156	490	1.0712
0.4241	500	1.0303
0.4326	510	1.0132
0.4411	520	1.0600
0.4495	530	0.8903
0.4580	540	0.8773
0.4665	550	1.0966
0.4750	560	1.1267
0.4835	570	0.9524
0.4919	580	1.0614
0.5004	590	1.0250
0.5089	600	0.7776
0.5174	610	0.8945
0.5259	620	0.5462
0.5344	630	0.9012
0.5428	640	1.0679
0.5513	650	0.7123
0.5598	660	0.8103
0.5683	670	0.6745
0.5768	680	0.8479
0.5852	690	0.8473
0.5937	700	0.9150
0.6022	710	0.5468
0.6107	720	0.7483
0.6192	730	0.9425
0.6277	740	0.7295
0.6361	750	0.8385
0.6446	760	0.8177
0.6531	770	0.7989
0.6616	780	0.7910
0.6701	790	0.6544
0.6785	800	0.9887
0.6870	810	0.6404
0.6955	820	0.8134
0.7040	830	0.5477
0.7125	840	0.7031
0.7209	850	0.7191
0.7294	860	0.7349
0.7379	870	0.8676
0.7464	880	0.6788
0.7549	890	0.7849
0.7634	900	0.7795
0.7718	910	0.8199
0.7803	920	0.7006
0.7888	930	0.6766
0.7973	940	0.7082
0.8058	950	0.7763
0.8142	960	0.7876
0.8227	970	0.8169
0.8312	980	0.6610
0.8397	990	0.8538
0.8482	1000	0.5989
0.8567	1010	0.7383
0.8651	1020	0.7147
0.8736	1030	0.7304
0.8821	1040	0.7192
0.8906	1050	0.7289
0.8991	1060	0.6387
0.9075	1070	0.5964
0.9160	1080	0.8195
0.9245	1090	0.6337
0.9330	1100	0.6402
0.9415	1110	0.7337
0.9500	1120	0.6287
0.9584	1130	0.6445
0.9669	1140	0.7259
0.9754	1150	0.7839
0.9839	1160	0.6223
0.9924	1170	0.7045
1.0008	1180	0.5581
1.0093	1190	0.5762
1.0178	1200	0.6059
1.0263	1210	0.6403
1.0348	1220	0.6196
1.0433	1230	0.6916
1.0517	1240	0.7460
1.0602	1250	0.5768
1.0687	1260	0.5439
1.0772	1270	0.6749
1.0857	1280	0.6286
1.0941	1290	0.7275
1.1026	1300	0.5483
1.1111	1310	0.5651
1.1196	1320	0.7014
1.1281	1330	0.6378
1.1366	1340	0.5440
1.1450	1350	0.7049
1.1535	1360	0.5390
1.1620	1370	0.6372
1.1705	1380	0.7674
1.1790	1390	0.5778
1.1874	1400	0.6669
1.1959	1410	0.6366
1.2044	1420	0.5297
1.2129	1430	0.6731
1.2214	1440	0.7272
1.2299	1450	0.5835
1.2383	1460	0.5759
1.2468	1470	0.6544
1.2553	1480	0.5855
1.2638	1490	0.6161
1.2723	1500	0.5341
1.2807	1510	0.7101
1.2892	1520	0.5991
1.2977	1530	0.6181
1.3062	1540	0.5412
1.3147	1550	0.6335
1.3232	1560	0.4617
1.3316	1570	0.6078
1.3401	1580	0.5664
1.3486	1590	0.4548
1.3571	1600	0.5480
1.3656	1610	0.6777
1.3740	1620	0.4901
1.3825	1630	0.5732
1.3910	1640	0.6267
1.3995	1650	0.6211
1.4080	1660	0.5107
1.4165	1670	0.4965
1.4249	1680	0.4756
1.4334	1690	0.6201
1.4419	1700	0.6060
1.4504	1710	0.5225
1.4589	1720	0.5140
1.4673	1730	0.5546
1.4758	1740	0.6196
1.4843	1750	0.5900
1.4928	1760	0.5839
1.5013	1770	0.5367
1.5098	1780	0.6249
1.5182	1790	0.4742
1.5267	1800	0.6129
1.5352	1810	0.5100
1.5437	1820	0.6051
1.5522	1830	0.5335
1.5606	1840	0.5096
1.5691	1850	0.5355
1.5776	1860	0.5281
1.5861	1870	0.6472
1.5946	1880	0.6264
1.6031	1890	0.4981
1.6115	1900	0.4401
1.6200	1910	0.4959
1.6285	1920	0.6478
1.6370	1930	0.5109
1.6455	1940	0.6202
1.6539	1950	0.6286
1.6624	1960	0.5406
1.6709	1970	0.5257
1.6794	1980	0.6998
1.6879	1990	0.5036
1.6964	2000	0.5581
1.7048	2010	0.5586
1.7133	2020	0.5199
1.7218	2030	0.5346
1.7303	2040	0.5688
1.7388	2050	0.5654
1.7472	2060	0.5735
1.7557	2070	0.4618
1.7642	2080	0.4923
1.7727	2090	0.4617
1.7812	2100	0.5193
1.7897	2110	0.6116
1.7981	2120	0.6135
1.8066	2130	0.4818
1.8151	2140	0.5521
1.8236	2150	0.5664
1.8321	2160	0.5185
1.8405	2170	0.4654
1.8490	2180	0.4675
1.8575	2190	0.4681
1.8660	2200	0.5867
1.8745	2210	0.4690
1.8830	2220	0.5602
1.8914	2230	0.5059
1.8999	2240	0.5971
1.9084	2250	0.5671
1.9169	2260	0.4636
1.9254	2270	0.4128
1.9338	2280	0.5535
1.9423	2290	0.5211
1.9508	2300	0.4354
1.9593	2310	0.5711
1.9678	2320	0.5789
1.9763	2330	0.5064
1.9847	2340	0.5665
1.9932	2350	0.5486
2.0017	2360	0.4541
2.0102	2370	0.4996
2.0187	2380	0.4554
2.0271	2390	0.5296
2.0356	2400	0.6290
2.0441	2410	0.5294
2.0526	2420	0.4837
2.0611	2430	0.5640
2.0696	2440	0.4845
2.0780	2450	0.5184
2.0865	2460	0.5202
2.0950	2470	0.5436
2.1035	2480	0.5087
2.1120	2490	0.4930
2.1204	2500	0.5346
2.1289	2510	0.4438
2.1374	2520	0.5001
2.1459	2530	0.5827
2.1544	2540	0.5700
2.1628	2550	0.4941
2.1713	2560	0.4896
2.1798	2570	0.5766
2.1883	2580	0.4674
2.1968	2590	0.5692
2.2053	2600	0.4569
2.2137	2610	0.5488
2.2222	2620	0.5426
2.2307	2630	0.5298
2.2392	2640	0.5127
2.2477	2650	0.5043
2.2561	2660	0.4980
2.2646	2670	0.5604
2.2731	2680	0.5107
2.2816	2690	0.4833
2.2901	2700	0.6057
2.2986	2710	0.5487
2.3070	2720	0.6312
2.3155	2730	0.4802
2.3240	2740	0.5626
2.3325	2750	0.5361
2.3410	2760	0.5074
2.3494	2770	0.5846
2.3579	2780	0.4857
2.3664	2790	0.5881
2.3749	2800	0.3761
2.3834	2810	0.4919
2.3919	2820	0.5354
2.4003	2830	0.4923
2.4088	2840	0.5929
2.4173	2850	0.4572
2.4258	2860	0.5131
2.4343	2870	0.4850
2.4427	2880	0.5409
2.4512	2890	0.5483
2.4597	2900	0.5252
2.4682	2910	0.5181
2.4767	2920	0.4834
2.4852	2930	0.4996
2.4936	2940	0.4852
2.5021	2950	0.5059
2.5106	2960	0.5016
2.5191	2970	0.4697
2.5276	2980	0.6227
2.5360	2990	0.4147
2.5445	3000	0.4348
2.5530	3010	0.4935
2.5615	3020	0.4841
2.5700	3030	0.5299
2.5785	3040	0.5956
2.5869	3050	0.5880
2.5954	3060	0.5062
2.6039	3070	0.5179
2.6124	3080	0.5290
2.6209	3090	0.4372
2.6293	3100	0.5652
2.6378	3110	0.5222
2.6463	3120	0.5589
2.6548	3130	0.4665
2.6633	3140	0.5182
2.6718	3150	0.6048
2.6802	3160	0.5209
2.6887	3170	0.4951
2.6972	3180	0.4705
2.7057	3190	0.4557
2.7142	3200	0.5273
2.7226	3210	0.4899
2.7311	3220	0.5317
2.7396	3230	0.5155
2.7481	3240	0.4674
2.7566	3250	0.4932
2.7651	3260	0.5774
2.7735	3270	0.4896
2.7820	3280	0.4601
2.7905	3290	0.5037
2.7990	3300	0.5724
2.8075	3310	0.4780
2.8159	3320	0.5556
2.8244	3330	0.4529
2.8329	3340	0.4963
2.8414	3350	0.4756
2.8499	3360	0.5187
2.8584	3370	0.5676
2.8668	3380	0.4204
2.8753	3390	0.4987
2.8838	3400	0.5173
2.8923	3410	0.5848
2.9008	3420	0.5046
2.9092	3430	0.5195
2.9177	3440	0.4605
2.9262	3450	0.4491
2.9347	3460	0.5506
2.9432	3470	0.4951
2.9517	3480	0.5290
2.9601	3490	0.4743
2.9686	3500	0.5898
2.9771	3510	0.4446
2.9856	3520	0.5059
2.9941	3530	0.5211
3.0025	3540	0.5688
3.0110	3550	0.5058
3.0195	3560	0.5003
3.0280	3570	0.5212
3.0365	3580	0.4837
3.0450	3590	0.4858
3.0534	3600	0.4779
3.0619	3610	0.5734
3.0704	3620	0.4780
3.0789	3630	0.4251
3.0874	3640	0.5297
3.0958	3650	0.4301
3.1043	3660	0.5491
3.1128	3670	0.5540
3.1213	3680	0.4716
3.1298	3690	0.4535
3.1383	3700	0.4965
3.1467	3710	0.5208
3.1552	3720	0.5274
3.1637	3730	0.5401
3.1722	3740	0.5869
3.1807	3750	0.5500
3.1891	3760	0.4793
3.1976	3770	0.5151
3.2061	3780	0.5416
3.2146	3790	0.5109
3.2231	3800	0.5302
3.2316	3810	0.4950
3.2400	3820	0.5823
3.2485	3830	0.4943
3.2570	3840	0.5190
3.2655	3850	0.4694
3.2740	3860	0.4608
3.2824	3870	0.5052
3.2909	3880	0.5065
3.2994	3890	0.5035
3.3079	3900	0.4862
3.3164	3910	0.5370
3.3249	3920	0.4426
3.3333	3930	0.4011
3.3418	3940	0.5025
3.3503	3950	0.5379
3.3588	3960	0.4854
3.3673	3970	0.4738
3.3757	3980	0.4677
3.3842	3990	0.4966
3.3927	4000	0.5211
3.4012	4010	0.4247
3.4097	4020	0.4725
3.4182	4030	0.4111
3.4266	4040	0.5796
3.4351	4050	0.4761
3.4436	4060	0.5138
3.4521	4070	0.5575
3.4606	4080	0.4206
3.4690	4090	0.4705
3.4775	4100	0.5302
3.4860	4110	0.5233
3.4945	4120	0.5259
3.5030	4130	0.5036
3.5115	4140	0.4798
3.5199	4150	0.4725
3.5284	4160	0.4625
3.5369	4170	0.5474
3.5454	4180	0.4464
3.5539	4190	0.5536
3.5623	4200	0.5558
3.5708	4210	0.5189
3.5793	4220	0.4841
3.5878	4230	0.4088
3.5963	4240	0.4857
3.6047	4250	0.4165
3.6132	4260	0.4420
3.6217	4270	0.5389
3.6302	4280	0.5001
3.6387	4290	0.4812
3.6472	4300	0.5215
3.6556	4310	0.5679
3.6641	4320	0.4882
3.6726	4330	0.5787
3.6811	4340	0.4132
3.6896	4350	0.4370
3.6980	4360	0.6031
3.7065	4370	0.5009
3.7150	4380	0.5619
3.7235	4390	0.4756
3.7320	4400	0.5222
3.7405	4410	0.5216
3.7489	4420	0.4569
3.7574	4430	0.4932
3.7659	4440	0.4852
3.7744	4450	0.5125
3.7829	4460	0.4744
3.7913	4470	0.5071
3.7998	4480	0.5042
3.8083	4490	0.4642
3.8168	4500	0.5199
3.8253	4510	0.5304
3.8338	4520	0.5035
3.8422	4530	0.5588
3.8507	4540	0.4863
3.8592	4550	0.4673
3.8677	4560	0.5302
3.8762	4570	0.4694
3.8846	4580	0.5405
3.8931	4590	0.4841
3.9016	4600	0.5430
3.9101	4610	0.5335
3.9186	4620	0.5308
3.9271	4630	0.5791
3.9355	4640	0.5085
3.9440	4650	0.5260
3.9525	4660	0.5110
3.9610	4670	0.4480
3.9695	4680	0.5914
3.9779	4690	0.4881
3.9864	4700	0.4869
3.9949	4710	0.4970
4.0034	4720	0.5309
4.0119	4730	0.4695
4.0204	4740	0.5106
4.0288	4750	0.5100
4.0373	4760	0.5291
4.0458	4770	0.4728
4.0543	4780	0.5145
4.0628	4790	0.5550
4.0712	4800	0.5192
4.0797	4810	0.4818
4.0882	4820	0.5379
4.0967	4830	0.4530
4.1052	4840	0.4719
4.1137	4850	0.5031
4.1221	4860	0.4867
4.1306	4870	0.4639
4.1391	4880	0.4390
4.1476	4890	0.4926
4.1561	4900	0.5361
4.1645	4910	0.4889
4.1730	4920	0.3853
4.1815	4930	0.5471
4.1900	4940	0.5115
4.1985	4950	0.5586
4.2070	4960	0.5272
4.2154	4970	0.5271
4.2239	4980	0.4684
4.2324	4990	0.5133
4.2409	5000	0.5973
4.2494	5010	0.4923
4.2578	5020	0.4629
4.2663	5030	0.4673
4.2748	5040	0.5141
4.2833	5050	0.5163
4.2918	5060	0.4898
4.3003	5070	0.4746
4.3087	5080	0.5307
4.3172	5090	0.4081
4.3257	5100	0.5066
4.3342	5110	0.5164
4.3427	5120	0.5030
4.3511	5130	0.5765
4.3596	5140	0.4530
4.3681	5150	0.5085
4.3766	5160	0.4275
4.3851	5170	0.4456
4.3936	5180	0.4491
4.4020	5190	0.4807
4.4105	5200	0.4843
4.4190	5210	0.5107
4.4275	5220	0.5204
4.4360	5230	0.5156
4.4444	5240	0.5067
4.4529	5250	0.4483
4.4614	5260	0.5092
4.4699	5270	0.4658
4.4784	5280	0.5014
4.4869	5290	0.4676
4.4953	5300	0.5119
4.5038	5310	0.5185
4.5123	5320	0.4460
4.5208	5330	0.4716
4.5293	5340	0.4775
4.5377	5350	0.4890
4.5462	5360	0.5026
4.5547	5370	0.5491
4.5632	5380	0.4686
4.5717	5390	0.3902
4.5802	5400	0.4809
4.5886	5410	0.4224
4.5971	5420	0.5018
4.6056	5430	0.4811
4.6141	5440	0.5390
4.6226	5450	0.4938
4.6310	5460	0.5181
4.6395	5470	0.4338
4.6480	5480	0.5351
4.6565	5490	0.4894
4.6650	5500	0.5117
4.6735	5510	0.4754
4.6819	5520	0.4154
4.6904	5530	0.5504
4.6989	5540	0.5428
4.7074	5550	0.5355
4.7159	5560	0.6427
4.7243	5570	0.4598
4.7328	5580	0.4769
4.7413	5590	0.4372
4.7498	5600	0.5851
4.7583	5610	0.4962
4.7668	5620	0.5619
4.7752	5630	0.4341
4.7837	5640	0.5026
4.7922	5650	0.5412
4.8007	5660	0.5126
4.8092	5670	0.4497
4.8176	5680	0.4663
4.8261	5690	0.5648
4.8346	5700	0.4492
4.8431	5710	0.3832
4.8516	5720	0.4533
4.8601	5730	0.5143
4.8685	5740	0.4881
4.8770	5750	0.4936
4.8855	5760	0.4669
4.8940	5770	0.5239
4.9025	5780	0.4696
4.9109	5790	0.5213
4.9194	5800	0.4941
4.9279	5810	0.4204
4.9364	5820	0.5003
4.9449	5830	0.5530
4.9534	5840	0.4430
4.9618	5850	0.5279
4.9703	5860	0.5658
4.9788	5870	0.4906
4.9873	5880	0.4429
4.9958	5890	0.5412

Training Time

Training: 5.6 minutes

Framework Versions

Python: 3.12.13
Sentence Transformers: 5.4.1
Transformers: 5.0.0
PyTorch: 2.10.0+cu128
Accelerate: 1.13.0
Datasets: 4.0.0
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",
}