CrossEncoder based on answerdotai/ModernBERT-base

This is a Cross Encoder model finetuned from answerdotai/ModernBERT-base 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: answerdotai/ModernBERT-base
Maximum Sequence Length: 8192 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': 'ModernBertForSequenceClassification'})
)

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-optim")
# 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.', '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.', '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.', '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)
# [0.8055 0.9977 0.9465 0.3779 0.5326]

# 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.',
    [
        '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.',
        '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.',
        '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: 16,402 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: 26.69 tokens
max: 53 tokens

min: 6 tokens
mean: 33.78 tokens
max: 349 tokens

min: 0.0
mean: 0.24
max: 1.0

	sentence1	sentence2	label
type	string	string	float
details	min: 9 tokens mean: 26.69 tokens max: 53 tokens	min: 6 tokens mean: 33.78 tokens max: 349 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.`	`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`
`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`

Loss: BinaryCrossEntropyLoss with these parameters:

{
    "activation_fn": "torch.nn.modules.linear.Identity",
    "pos_weight": 2.9791362285614014
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
learning_rate: 5.313895255344898e-06
weight_decay: 0.01
num_train_epochs: 6
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: 5.313895255344898e-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: 6
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
0.0097	10	1.1175
0.0195	20	1.1009
0.0292	30	1.1173
0.0390	40	1.1408
0.0487	50	1.1205
0.0585	60	1.0845
0.0682	70	1.0591
0.0780	80	1.0761
0.0877	90	1.0539
0.0975	100	1.0003
0.1072	110	1.0794
0.1170	120	0.9878
0.1267	130	1.1186
0.1365	140	1.0896
0.1462	150	1.0092
0.1559	160	1.0853
0.1657	170	1.0927
0.1754	180	1.0673
0.1852	190	0.9538
0.1949	200	1.0377
0.2047	210	0.9825
0.2144	220	1.0387
0.2242	230	1.0627
0.2339	240	1.0062
0.2437	250	1.0111
0.2534	260	1.0186
0.2632	270	1.0716
0.2729	280	1.0317
0.2827	290	1.0562
0.2924	300	1.0639
0.3021	310	1.0376
0.3119	320	1.0246
0.3216	330	1.0441
0.3314	340	0.9686
0.3411	350	0.9936
0.3509	360	1.0146
0.3606	370	1.0225
0.3704	380	1.0101
0.3801	390	1.1048
0.3899	400	1.0480
0.3996	410	1.0071
0.4094	420	1.1171
0.4191	430	1.0599
0.4288	440	1.0391
0.4386	450	1.0264
0.4483	460	1.0056
0.4581	470	1.0159
0.4678	480	0.9445
0.4776	490	1.0964
0.4873	500	0.9996
0.4971	510	1.0448
0.5068	520	1.1087
0.5166	530	1.0376
0.5263	540	0.9959
0.5361	550	0.9939
0.5458	560	0.9432
0.5556	570	0.9152
0.5653	580	1.0212
0.5750	590	0.9678
0.5848	600	1.0339
0.5945	610	0.9964
0.6043	620	0.9919
0.6140	630	0.9314
0.6238	640	1.2510
0.6335	650	0.9553
0.6433	660	1.0274
0.6530	670	1.0217
0.6628	680	0.9615
0.6725	690	1.1405
0.6823	700	0.9128
0.6920	710	1.0212
0.7018	720	1.0171
0.7115	730	0.9644
0.7212	740	0.9432
0.7310	750	1.1639
0.7407	760	1.0445
0.7505	770	1.0069
0.7602	780	1.0769
0.7700	790	1.0117
0.7797	800	1.0092
0.7895	810	0.9908
0.7992	820	1.0575
0.8090	830	0.9566
0.8187	840	0.9870
0.8285	850	1.0237
0.8382	860	0.9338
0.8480	870	1.1327
0.8577	880	0.9714
0.8674	890	0.9173
0.8772	900	1.0236
0.8869	910	1.0148
0.8967	920	0.9902
0.9064	930	0.9618
0.9162	940	1.0532
0.9259	950	1.0211
0.9357	960	0.9667
0.9454	970	0.9785
0.9552	980	0.8634
0.9649	990	0.9606
0.9747	1000	1.0890
0.9844	1010	0.9633
0.9942	1020	0.9641
1.0039	1030	1.0221
1.0136	1040	1.0100
1.0234	1050	0.9710
1.0331	1060	0.8320
1.0429	1070	0.8211
1.0526	1080	1.0451
1.0624	1090	0.8954
1.0721	1100	1.0474
1.0819	1110	1.0595
1.0916	1120	0.8930
1.1014	1130	0.9947
1.1111	1140	1.0077
1.1209	1150	0.9637
1.1306	1160	0.9821
1.1404	1170	1.0375
1.1501	1180	0.8805
1.1598	1190	0.8931
1.1696	1200	0.9411
1.1793	1210	1.0276
1.1891	1220	0.9195
1.1988	1230	0.9460
1.2086	1240	0.9493
1.2183	1250	0.9010
1.2281	1260	0.8917
1.2378	1270	1.0196
1.2476	1280	1.0238
1.2573	1290	1.0325
1.2671	1300	1.0315
1.2768	1310	0.9870
1.2865	1320	1.0465
1.2963	1330	0.9335
1.3060	1340	0.9411
1.3158	1350	0.9471
1.3255	1360	0.9261
1.3353	1370	1.0126
1.3450	1380	0.8594
1.3548	1390	0.8929
1.3645	1400	1.0333
1.3743	1410	1.0118
1.3840	1420	0.9895
1.3938	1430	0.9721
1.4035	1440	0.9228
1.4133	1450	1.0069
1.4230	1460	1.0970
1.4327	1470	0.9616
1.4425	1480	0.9229
1.4522	1490	1.0102
1.4620	1500	0.9860
1.4717	1510	0.9923
1.4815	1520	0.9470
1.4912	1530	0.9126
1.5010	1540	0.9449
1.5107	1550	0.8780
1.5205	1560	0.8965
1.5302	1570	0.8886
1.5400	1580	0.9948
1.5497	1590	0.9499
1.5595	1600	0.8638
1.5692	1610	0.9415
1.5789	1620	1.0008
1.5887	1630	0.9427
1.5984	1640	0.9332
1.6082	1650	0.9121
1.6179	1660	0.9996
1.6277	1670	0.9956
1.6374	1680	0.9493
1.6472	1690	0.8697
1.6569	1700	0.9344
1.6667	1710	0.9429
1.6764	1720	0.9071
1.6862	1730	0.9841
1.6959	1740	0.8157
1.7057	1750	0.9267
1.7154	1760	0.9017
1.7251	1770	0.9561
1.7349	1780	0.9515
1.7446	1790	0.7276
1.7544	1800	0.9253
1.7641	1810	1.0405
1.7739	1820	0.9730
1.7836	1830	1.0187
1.7934	1840	0.8832
1.8031	1850	0.8789
1.8129	1860	0.9784
1.8226	1870	0.9431
1.8324	1880	0.9205
1.8421	1890	0.8091
1.8519	1900	0.9072
1.8616	1910	0.9246
1.8713	1920	0.9807
1.8811	1930	0.9941
1.8908	1940	0.9263
1.9006	1950	1.0359
1.9103	1960	0.8352
1.9201	1970	0.9291
1.9298	1980	0.9837
1.9396	1990	0.8630
1.9493	2000	0.9079
1.9591	2010	0.9462
1.9688	2020	0.9100
1.9786	2030	0.9491
1.9883	2040	0.9448
1.9981	2050	1.0338
2.0078	2060	0.8081
2.0175	2070	0.8471
2.0273	2080	0.7977
2.0370	2090	0.9369
2.0468	2100	0.8644
2.0565	2110	0.8807
2.0663	2120	0.9113
2.0760	2130	0.8669
2.0858	2140	0.8431
2.0955	2150	0.9536
2.1053	2160	0.9920
2.1150	2170	0.8974
2.1248	2180	0.7341
2.1345	2190	0.9012
2.1442	2200	0.8155
2.1540	2210	0.9269
2.1637	2220	0.9211
2.1735	2230	0.8944
2.1832	2240	0.8326
2.1930	2250	0.8492
2.2027	2260	0.8054
2.2125	2270	0.8507
2.2222	2280	1.0351
2.2320	2290	0.8179
2.2417	2300	0.9241
2.2515	2310	0.8834
2.2612	2320	0.8550
2.2710	2330	0.8042
2.2807	2340	0.9430
2.2904	2350	0.9298
2.3002	2360	0.8427
2.3099	2370	0.8538
2.3197	2380	0.7924
2.3294	2390	0.9096
2.3392	2400	0.8535
2.3489	2410	0.8615
2.3587	2420	0.8039
2.3684	2430	1.1530
2.3782	2440	0.9399
2.3879	2450	0.8225
2.3977	2460	0.8961
2.4074	2470	0.8224
2.4172	2480	0.8830
2.4269	2490	0.7538
2.4366	2500	0.8589
2.4464	2510	0.9339
2.4561	2520	0.9337
2.4659	2530	0.9120
2.4756	2540	0.8140
2.4854	2550	0.9948
2.4951	2560	0.9354
2.5049	2570	0.7329
2.5146	2580	0.9223
2.5244	2590	0.8645
2.5341	2600	0.7594
2.5439	2610	0.8204
2.5536	2620	0.7885
2.5634	2630	0.7610
2.5731	2640	0.8186
2.5828	2650	1.0073
2.5926	2660	0.7852
2.6023	2670	0.8180
2.6121	2680	0.8214
2.6218	2690	0.8927
2.6316	2700	0.7664
2.6413	2710	0.8724
2.6511	2720	0.8113
2.6608	2730	0.8118
2.6706	2740	0.7959
2.6803	2750	0.7683
2.6901	2760	0.8668
2.6998	2770	0.8547
2.7096	2780	0.7966
2.7193	2790	0.8516
2.7290	2800	0.7918
2.7388	2810	0.8746
2.7485	2820	0.7798
2.7583	2830	0.8889
2.7680	2840	0.7685
2.7778	2850	0.7267
2.7875	2860	0.7938
2.7973	2870	0.9610
2.8070	2880	0.8677
2.8168	2890	0.7550
2.8265	2900	0.7623
2.8363	2910	0.8598
2.8460	2920	0.7136
2.8558	2930	0.7466
2.8655	2940	0.8219
2.8752	2950	0.7956
2.8850	2960	0.6981
2.8947	2970	0.9254
2.9045	2980	0.8840
2.9142	2990	0.9868
2.9240	3000	0.9453
2.9337	3010	0.8628
2.9435	3020	0.9542
2.9532	3030	0.8349
2.9630	3040	0.7961
2.9727	3050	0.9366
2.9825	3060	0.6620
2.9922	3070	0.7554
3.0019	3080	0.9036
3.0117	3090	0.6855
3.0214	3100	0.7401
3.0312	3110	0.7356
3.0409	3120	0.7820
3.0507	3130	0.7523
3.0604	3140	0.6595
3.0702	3150	0.8032
3.0799	3160	0.7540
3.0897	3170	0.7400
3.0994	3180	0.7961
3.1092	3190	0.7674
3.1189	3200	0.8115
3.1287	3210	0.8753
3.1384	3220	0.8289
3.1481	3230	0.7366
3.1579	3240	0.7117
3.1676	3250	0.7534
3.1774	3260	0.8592
3.1871	3270	0.7792
3.1969	3280	0.7716
3.2066	3290	0.7162
3.2164	3300	0.7365
3.2261	3310	0.6687
3.2359	3320	0.7656
3.2456	3330	0.7796
3.2554	3340	0.6275
3.2651	3350	0.7196
3.2749	3360	0.7319
3.2846	3370	0.6622
3.2943	3380	0.8410
3.3041	3390	0.7733
3.3138	3400	0.8076
3.3236	3410	0.6804
3.3333	3420	0.7294
3.3431	3430	0.8296
3.3528	3440	0.7692
3.3626	3450	0.6658
3.3723	3460	0.6681
3.3821	3470	0.7325
3.3918	3480	0.8206
3.4016	3490	0.7718
3.4113	3500	0.7683
3.4211	3510	0.8903
3.4308	3520	0.6322
3.4405	3530	0.7339
3.4503	3540	0.7571
3.4600	3550	0.8536
3.4698	3560	0.7135
3.4795	3570	0.7895
3.4893	3580	0.7343
3.4990	3590	0.6025
3.5088	3600	0.7438
3.5185	3610	0.6286
3.5283	3620	0.7607
3.5380	3630	0.8118
3.5478	3640	0.6794
3.5575	3650	0.6324
3.5673	3660	0.7903
3.5770	3670	0.7422
3.5867	3680	0.7545
3.5965	3690	0.7505
3.6062	3700	0.6024
3.6160	3710	0.6948
3.6257	3720	0.6460
3.6355	3730	0.6820
3.6452	3740	0.6075
3.6550	3750	0.9157
3.6647	3760	0.6355
3.6745	3770	0.6677
3.6842	3780	0.7564
3.6940	3790	0.7790
3.7037	3800	0.7102
3.7135	3810	0.7789
3.7232	3820	0.6921
3.7329	3830	0.7073
3.7427	3840	0.7365
3.7524	3850	0.6600
3.7622	3860	0.7297
3.7719	3870	0.7249
3.7817	3880	0.8011
3.7914	3890	0.8130
3.8012	3900	0.7234
3.8109	3910	0.6838
3.8207	3920	0.7096
3.8304	3930	0.7868
3.8402	3940	0.7928
3.8499	3950	0.6900
3.8596	3960	0.7295
3.8694	3970	0.6618
3.8791	3980	0.6916
3.8889	3990	0.8056
3.8986	4000	0.7683
3.9084	4010	0.5421
3.9181	4020	0.8662
3.9279	4030	0.6936
3.9376	4040	0.5801
3.9474	4050	0.7655
3.9571	4060	0.6983
3.9669	4070	0.7662
3.9766	4080	0.6106
3.9864	4090	0.5913
3.9961	4100	0.6509
4.0058	4110	0.6910
4.0156	4120	0.5405
4.0253	4130	0.6803
4.0351	4140	0.5957
4.0448	4150	0.5514
4.0546	4160	0.5638
4.0643	4170	0.5482
4.0741	4180	0.5582
4.0838	4190	0.6412
4.0936	4200	0.6030
4.1033	4210	0.6077
4.1131	4220	0.4956
4.1228	4230	0.6831
4.1326	4240	0.5686
4.1423	4250	0.5867
4.1520	4260	0.5407
4.1618	4270	0.7225
4.1715	4280	0.6058
4.1813	4290	0.5480
4.1910	4300	0.5814
4.2008	4310	0.6253
4.2105	4320	0.5421
4.2203	4330	0.5345
4.2300	4340	0.6734
4.2398	4350	0.6326
4.2495	4360	0.7275
4.2593	4370	0.7994
4.2690	4380	0.6813
4.2788	4390	0.6693
4.2885	4400	0.6438
4.2982	4410	0.5521
4.3080	4420	0.5758
4.3177	4430	0.6022
4.3275	4440	0.5740
4.3372	4450	0.7076
4.3470	4460	0.5725
4.3567	4470	0.6789
4.3665	4480	0.5883
4.3762	4490	0.6141
4.3860	4500	0.5579
4.3957	4510	0.5301
4.4055	4520	0.7434
4.4152	4530	0.7694
4.4250	4540	0.7008
4.4347	4550	0.6194
4.4444	4560	0.7417
4.4542	4570	0.6002
4.4639	4580	0.6270
4.4737	4590	0.5524
4.4834	4600	0.4945
4.4932	4610	0.6156
4.5029	4620	0.4459
4.5127	4630	0.6352
4.5224	4640	0.7052
4.5322	4650	0.5383
4.5419	4660	0.7233
4.5517	4670	0.7383
4.5614	4680	0.4743
4.5712	4690	0.5934
4.5809	4700	0.5835
4.5906	4710	0.5183
4.6004	4720	0.6195
4.6101	4730	0.6750
4.6199	4740	0.6079
4.6296	4750	0.6703
4.6394	4760	0.6492
4.6491	4770	0.5025
4.6589	4780	0.5318
4.6686	4790	0.5101
4.6784	4800	0.5775
4.6881	4810	0.5110
4.6979	4820	0.6306
4.7076	4830	0.6114
4.7173	4840	0.7088
4.7271	4850	0.5576
4.7368	4860	0.4996
4.7466	4870	0.7594
4.7563	4880	0.6202
4.7661	4890	0.6331
4.7758	4900	0.6066
4.7856	4910	0.5998
4.7953	4920	0.7323
4.8051	4930	0.4995
4.8148	4940	0.6681
4.8246	4950	0.6301
4.8343	4960	0.6836
4.8441	4970	0.5600
4.8538	4980	0.6109
4.8635	4990	0.5034
4.8733	5000	0.6033
4.8830	5010	0.5312
4.8928	5020	0.6719
4.9025	5030	0.6565
4.9123	5040	0.6241
4.9220	5050	0.5467
4.9318	5060	0.5449
4.9415	5070	0.6176
4.9513	5080	0.5887
4.9610	5090	0.6441
4.9708	5100	0.6435
4.9805	5110	0.5699
4.9903	5120	0.5030
5.0	5130	0.5826
5.0097	5140	0.4929
5.0195	5150	0.4805
5.0292	5160	0.4845
5.0390	5170	0.6884
5.0487	5180	0.4275
5.0585	5190	0.5615
5.0682	5200	0.4838
5.0780	5210	0.3965
5.0877	5220	0.6133
5.0975	5230	0.5513
5.1072	5240	0.4324
5.1170	5250	0.4897
5.1267	5260	0.4277
5.1365	5270	0.6630
5.1462	5280	0.5279
5.1559	5290	0.4980
5.1657	5300	0.5722
5.1754	5310	0.5021
5.1852	5320	0.5915
5.1949	5330	0.4906
5.2047	5340	0.4172
5.2144	5350	0.5690
5.2242	5360	0.4365
5.2339	5370	0.5416
5.2437	5380	0.4935
5.2534	5390	0.5398
5.2632	5400	0.5167
5.2729	5410	0.5277
5.2827	5420	0.5646
5.2924	5430	0.5852
5.3021	5440	0.4689
5.3119	5450	0.5197
5.3216	5460	0.5047
5.3314	5470	0.4488
5.3411	5480	0.4446
5.3509	5490	0.6019
5.3606	5500	0.4333
5.3704	5510	0.4895
5.3801	5520	0.5465
5.3899	5530	0.5216
5.3996	5540	0.4350
5.4094	5550	0.4717
5.4191	5560	0.5793
5.4288	5570	0.5391
5.4386	5580	0.4375
5.4483	5590	0.5046
5.4581	5600	0.5550
5.4678	5610	0.5494
5.4776	5620	0.3586
5.4873	5630	0.5062
5.4971	5640	0.4894
5.5068	5650	0.4966
5.5166	5660	0.5321
5.5263	5670	0.4398
5.5361	5680	0.3831
5.5458	5690	0.6391
5.5556	5700	0.4640
5.5653	5710	0.4914
5.5750	5720	0.5066
5.5848	5730	0.5746
5.5945	5740	0.4817
5.6043	5750	0.5090
5.6140	5760	0.3478
5.6238	5770	0.5423
5.6335	5780	0.4103
5.6433	5790	0.4735
5.6530	5800	0.4723
5.6628	5810	0.4193
5.6725	5820	0.4541
5.6823	5830	0.5544
5.6920	5840	0.6021
5.7018	5850	0.5674
5.7115	5860	0.4728
5.7212	5870	0.4923
5.7310	5880	0.4805
5.7407	5890	0.5123
5.7505	5900	0.4647
5.7602	5910	0.5473
5.7700	5920	0.5116
5.7797	5930	0.4552
5.7895	5940	0.5400
5.7992	5950	0.5776
5.8090	5960	0.4331
5.8187	5970	0.4874
5.8285	5980	0.5218
5.8382	5990	0.6322
5.8480	6000	0.4923
5.8577	6010	0.3710
5.8674	6020	0.5147
5.8772	6030	0.4702
5.8869	6040	0.4489
5.8967	6050	0.4997
5.9064	6060	0.5323
5.9162	6070	0.5768
5.9259	6080	0.5449
5.9357	6090	0.4726
5.9454	6100	0.3773
5.9552	6110	0.4525
5.9649	6120	0.6072
5.9747	6130	0.5258
5.9844	6140	0.5080
5.9942	6150	0.5628

Training Time

Training: 26.1 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",
}