aditeyabaral-redis/langcache-reranker-v1

Redis fine-tuned CrossEncoder model for semantic caching on LangCache

This is a Cross Encoder model finetuned from Alibaba-NLP/gte-reranker-modernbert-base on the LangCache Sentence Pairs (all) dataset using the sentence-transformers library. It computes scores for pairs of texts, which can be used for sentence pair classification.

Model Details

Model Description

• Model Type: Cross Encoder
• Base model: Alibaba-NLP/gte-reranker-modernbert-base
• Maximum Sequence Length: 8192 tokens
• Number of Output Labels: 1 label
• Training Dataset:
  • LangCache Sentence Pairs (all)
• Language: en
• License: apache-2.0

Model Sources

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

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("aditeyabaral-redis/langcache-reranker-v1")
# Get scores for pairs of texts
pairs = [
    ['The newer Punts are still very much in existence today and race in the same fleets as the older boats .', 'The newer punts are still very much in existence today and run in the same fleets as the older boats .'],
    ['Turner Valley , was at the Turner Valley Bar N Ranch Airport , southwest of the Turner Valley Bar N Ranch , Alberta , Canada .', 'Turner Valley Bar N Ranch Airport , , was located at Turner Valley Bar N Ranch , southwest of Turner Valley , Alberta , Canada .'],
    ['After losing his second election , he resigned as opposition leader and was replaced by Geoff Pearsall .', 'Max Bingham resigned as opposition leader after losing his second election , and was replaced by Geoff Pearsall .'],
    ['She married Peter Haygarth on 29 May 1964 in Durban . Her second marriage , to Robin Osborne , took place in 1977 .', 'She married Robin Osborne on May 29 , 1964 in Durban , and her second marriage with Peter Haygarth took place in 1977 .'],
    ['In 2005 she moved to Norway , settled in Geilo and worked as a rafting guide , in 2006 she started mountain biking - races .', 'In 2005 , she moved to Geilo , settling in Norway and worked as a rafting guide . She started mountain bike races in 2006 .'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'The newer Punts are still very much in existence today and race in the same fleets as the older boats .',
    [
        'The newer punts are still very much in existence today and run in the same fleets as the older boats .',
        'Turner Valley Bar N Ranch Airport , , was located at Turner Valley Bar N Ranch , southwest of Turner Valley , Alberta , Canada .',
        'Max Bingham resigned as opposition leader after losing his second election , and was replaced by Geoff Pearsall .',
        'She married Robin Osborne on May 29 , 1964 in Durban , and her second marriage with Peter Haygarth took place in 1977 .',
        'In 2005 , she moved to Geilo , settling in Norway and worked as a rafting guide . She started mountain bike races in 2006 .',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Evaluation

Metrics

Cross Encoder Classification

• Datasets: val and test
• Evaluated with CrossEncoderClassificationEvaluator

Metric	val	test
accuracy	0.7718	0.8947
accuracy_threshold	0.8927	0.8616
f1	0.6934	0.8797
f1_threshold	0.8759	0.5037
precision	0.6788	0.8643
recall	0.7086	0.8957
average_precision	0.7676	0.9345

Training Details

Training Dataset

LangCache Sentence Pairs (all)

• Dataset: LangCache Sentence Pairs (all)
• Size: 62,021 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 27 characters mean: 112.72 characters max: 197 characters	min: 27 characters mean: 112.54 characters max: 198 characters	0: ~50.30% 1: ~49.70%

• Samples:

  sentence1	sentence2	label
  The newer Punts are still very much in existence today and race in the same fleets as the older boats .	The newer punts are still very much in existence today and run in the same fleets as the older boats .	1
  Turner Valley , was at the Turner Valley Bar N Ranch Airport , southwest of the Turner Valley Bar N Ranch , Alberta , Canada .	Turner Valley Bar N Ranch Airport , , was located at Turner Valley Bar N Ranch , southwest of Turner Valley , Alberta , Canada .	0
  After losing his second election , he resigned as opposition leader and was replaced by Geoff Pearsall .	Max Bingham resigned as opposition leader after losing his second election , and was replaced by Geoff Pearsall .	1

• Loss: BinaryCrossEntropyLoss with these parameters:

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

Evaluation Dataset

LangCache Sentence Pairs (all)

• Dataset: LangCache Sentence Pairs (all)
• Size: 62,021 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 27 characters mean: 112.72 characters max: 197 characters	min: 27 characters mean: 112.54 characters max: 198 characters	0: ~50.30% 1: ~49.70%

• Samples:

  sentence1	sentence2	label
  The newer Punts are still very much in existence today and race in the same fleets as the older boats .	The newer punts are still very much in existence today and run in the same fleets as the older boats .	1
  Turner Valley , was at the Turner Valley Bar N Ranch Airport , southwest of the Turner Valley Bar N Ranch , Alberta , Canada .	Turner Valley Bar N Ranch Airport , , was located at Turner Valley Bar N Ranch , southwest of Turner Valley , Alberta , Canada .	0
  After losing his second election , he resigned as opposition leader and was replaced by Geoff Pearsall .	Max Bingham resigned as opposition leader after losing his second election , and was replaced by Geoff Pearsall .	1

• Loss: BinaryCrossEntropyLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 48
• per_device_eval_batch_size: 48
• learning_rate: 0.0002
• num_train_epochs: 50
• warmup_steps: 1000
• load_best_model_at_end: True
• optim: adamw_torch
• push_to_hub: True
• hub_model_id: aditeyabaral-redis/langcache-reranker-v1

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 48
• per_device_eval_batch_size: 48
• 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: 0.0002
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 50
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• warmup_steps: 1000
• 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: False
• 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: True
• 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: True
• 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: True
• resume_from_checkpoint: None
• hub_model_id: aditeyabaral-redis/langcache-reranker-v1
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• hub_revision: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• 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
• 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
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: True
• 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	Validation Loss	val_average_precision	test_average_precision
-1	-1	-	-	0.7676	0.6907
0.1833	1000	0.2986	0.3912	-	0.8585
0.3666	2000	0.2465	0.3856	-	0.8956
0.5499	3000	0.2287	0.3362	-	0.9160
0.7331	4000	0.2171	0.3408	-	0.9071
0.9164	5000	0.2068	0.3182	-	0.9220
1.0997	6000	0.1991	0.3458	-	0.8686
1.2830	7000	0.1939	0.3188	-	0.9244
1.4663	8000	0.1917	0.3120	-	0.9287
1.6496	9000	0.1906	0.3015	-	0.9279
1.8328	10000	0.1884	0.2986	-	0.9316
2.0161	11000	0.183	0.3065	-	0.9320
2.1994	12000	0.1714	0.3046	-	0.9180
2.3827	13000	0.1738	0.2994	-	0.9315
2.5660	14000	0.1709	0.2965	-	0.9347
2.7493	15000	0.1717	0.2911	-	0.9309
2.9326	16000	0.1698	0.2900	-	0.9354
3.1158	17000	0.16	0.2894	-	0.9377
3.2991	18000	0.1589	0.2830	-	0.9356
3.4824	19000	0.1574	0.2829	-	0.9337
3.6657	20000	0.1572	0.2818	-	0.9324
3.8490	21000	0.1587	0.2866	-	0.9365
4.0323	22000	0.1543	0.2923	-	0.9389
4.2155	23000	0.1445	0.2871	-	0.9430
4.3988	24000	0.1447	0.2793	-	0.9429
4.5821	25000	0.1473	0.2791	-	0.9386
4.7654	26000	0.146	0.2700	-	0.9417
4.9487	27000	0.1473	0.2697	-	0.9419
5.1320	28000	0.1365	0.2810	-	0.9411
5.3152	29000	0.1331	0.2764	-	0.9397
5.4985	30000	0.1372	0.2794	-	0.9416
5.6818	31000	0.1365	0.2751	-	0.9408
5.8651	32000	0.1365	0.2724	-	0.9411
6.0484	33000	0.1348	0.2767	-	0.9378
6.2317	34000	0.1236	0.2840	-	0.9388
6.4150	35000	0.1262	0.2845	-	0.9437
6.5982	36000	0.1277	0.2781	-	0.9446
6.7815	37000	0.129	0.2705	-	0.9427
6.9648	38000	0.1279	0.2773	-	0.9381
7.1481	39000	0.1173	0.2875	-	0.9420
7.3314	40000	0.1175	0.2901	-	0.9438
7.5147	41000	0.1174	0.2787	-	0.9420
7.6979	42000	0.118	0.2879	-	0.9424
7.8812	43000	0.1201	0.2826	-	0.9450
8.0645	44000	0.1168	0.2851	-	0.9419
8.2478	45000	0.1062	0.2913	-	0.9450
8.4311	46000	0.1091	0.2918	-	0.9454
8.6144	47000	0.1117	0.2799	-	0.9445
8.7977	48000	0.1123	0.2762	-	0.9443
8.9809	49000	0.1132	0.2772	-	0.9455
9.1642	50000	0.1016	0.2943	-	0.9433
9.3475	51000	0.1012	0.2879	-	0.9441
9.5308	52000	0.1029	0.2851	-	0.9442
9.7141	53000	0.105	0.2905	-	0.9448
9.8974	54000	0.1062	0.2960	-	0.9425
10.0806	55000	0.0996	0.2984	-	0.9430
10.2639	56000	0.0924	0.2947	-	0.9432
10.4472	57000	0.0939	0.2918	-	0.9421
10.6305	58000	0.0977	0.2895	-	0.9438
10.8138	59000	0.0977	0.2905	-	0.9446
10.9971	60000	0.0985	0.2882	-	0.9403
11.1804	61000	0.0857	0.3025	-	0.9435
11.3636	62000	0.0869	0.2997	-	0.9450
11.5469	63000	0.0886	0.3025	-	0.9459
11.7302	64000	0.0901	0.3000	-	0.9443
11.9135	65000	0.092	0.2913	-	0.9424
12.0968	66000	0.085	0.3017	-	0.9443
12.2801	67000	0.0801	0.3101	-	0.9449
12.4633	68000	0.0823	0.3018	-	0.9468
12.6466	69000	0.0841	0.2971	-	0.9457
12.8299	70000	0.0855	0.3063	-	0.9428
13.0132	71000	0.0854	0.3105	-	0.9436
13.1965	72000	0.0744	0.3017	-	0.9451
13.3798	73000	0.0763	0.3024	-	0.9425
13.5630	74000	0.0777	0.2948	-	0.9461
13.7463	75000	0.0791	0.3006	-	0.9466
13.9296	76000	0.0803	0.3001	-	0.9446
14.1129	77000	0.0721	0.3229	-	0.9445
14.2962	78000	0.0692	0.3231	-	0.9437
14.4795	79000	0.0703	0.3242	-	0.9458
14.6628	80000	0.073	0.3078	-	0.9469
14.8460	81000	0.073	0.3111	-	0.9448
15.0293	82000	0.0731	0.3319	-	0.9459
15.2126	83000	0.0629	0.3094	-	0.9464
15.3959	84000	0.0644	0.3440	-	0.9427
15.5792	85000	0.0673	0.3234	-	0.9457
15.7625	86000	0.068	0.3192	-	0.9430
15.9457	87000	0.0687	0.3097	-	0.9428
16.1290	88000	0.0618	0.3379	-	0.9466
16.3123	89000	0.0615	0.3192	-	0.9436
16.4956	90000	0.0605	0.3303	-	0.9452
16.6789	91000	0.0635	0.3154	-	0.9445
16.8622	92000	0.0637	0.3324	-	0.9467
17.0455	93000	0.0615	0.3365	-	0.9424
17.2287	94000	0.056	0.3332	-	0.9446
17.4120	95000	0.0567	0.3412	-	0.9432
17.5953	96000	0.0571	0.3419	-	0.9444
17.7786	97000	0.0589	0.3271	-	0.9403
17.9619	98000	0.0588	0.3281	-	0.9440
18.1452	99000	0.053	0.3282	-	0.9475
18.3284	100000	0.0525	0.3414	-	0.9470
18.5117	101000	0.0528	0.3263	-	0.9450
18.6950	102000	0.0539	0.3363	-	0.9428
18.8783	103000	0.056	0.3487	-	0.9454
19.0616	104000	0.0528	0.3701	-	0.9465
19.2449	105000	0.0464	0.3877	-	0.9328
19.4282	106000	0.0499	0.3379	-	0.9451
19.6114	107000	0.0496	0.3500	-	0.9442
19.7947	108000	0.0502	0.3420	-	0.9444
19.9780	109000	0.0519	0.3459	-	0.9442
20.1613	110000	0.0443	0.3755	-	0.9449
20.3446	111000	0.0449	0.3588	-	0.9447
20.5279	112000	0.0448	0.3616	-	0.9448
20.7111	113000	0.0471	0.3463	-	0.9426
20.8944	114000	0.0474	0.3784	-	0.9400
21.0777	115000	0.0451	0.3493	-	0.9447
21.2610	116000	0.0415	0.3633	-	0.9448
21.4443	117000	0.0412	0.3635	-	0.9472
21.6276	118000	0.0441	0.3710	-	0.9454
21.8109	119000	0.0427	0.3696	-	0.9459
21.9941	120000	0.045	0.3571	-	0.9440
22.1774	121000	0.0384	0.3815	-	0.9431
22.3607	122000	0.0389	0.3832	-	0.9428
22.5440	123000	0.0397	0.3773	-	0.9461
22.7273	124000	0.0402	0.3977	-	0.9415
22.9106	125000	0.0399	0.3870	-	0.9354
23.0938	126000	0.0376	0.3820	-	0.9409
23.2771	127000	0.0362	0.3755	-	0.9411
23.4604	128000	0.0358	0.3915	-	0.9461
23.6437	129000	0.0368	0.3688	-	0.9411
23.8270	130000	0.0374	0.4068	-	0.9427
24.0103	131000	0.0376	0.4155	-	0.9445
24.1935	132000	0.0325	0.3967	-	0.9434
24.3768	133000	0.0333	0.4209	-	0.9425
24.5601	134000	0.0335	0.4018	-	0.9432
24.7434	135000	0.0343	0.4250	-	0.9443
24.9267	136000	0.0345	0.4185	-	0.9414
25.1100	137000	0.0316	0.4075	-	0.9454
25.2933	138000	0.0299	0.4096	-	0.9454
25.4765	139000	0.0294	0.4135	-	0.9459
25.6598	140000	0.0317	0.3997	-	0.9445
25.8431	141000	0.0328	0.4093	-	0.9438
26.0264	142000	0.0317	0.4361	-	0.9404
26.2097	143000	0.027	0.4347	-	0.9454
26.3930	144000	0.0281	0.4149	-	0.9413
26.5762	145000	0.0283	0.4151	-	0.9454
26.7595	146000	0.0302	0.4041	-	0.9416
26.9428	147000	0.0301	0.4265	-	0.9340
27.1261	148000	0.026	0.4223	-	0.9426
27.3094	149000	0.0267	0.4237	-	0.9430
27.4927	150000	0.0268	0.4281	-	0.9458
27.6760	151000	0.0262	0.4193	-	0.9426
27.8592	152000	0.0262	0.4412	-	0.9402
28.0425	153000	0.0261	0.4795	-	0.9425
28.2258	154000	0.024	0.4519	-	0.9442
28.4091	155000	0.024	0.4395	-	0.9440
28.5924	156000	0.025	0.4549	-	0.9456
28.7757	157000	0.0253	0.4446	-	0.9429
28.9589	158000	0.0258	0.4349	-	0.9425
29.1422	159000	0.0211	0.4490	-	0.9430
29.3255	160000	0.0218	0.4538	-	0.9455
29.5088	161000	0.0217	0.4771	-	0.9435
29.6921	162000	0.0228	0.4238	-	0.9440
29.8754	163000	0.022	0.4731	-	0.9412
30.0587	164000	0.0227	0.4630	-	0.9450
30.2419	165000	0.0197	0.4840	-	0.9453
30.4252	166000	0.0198	0.4799	-	0.9434
30.6085	167000	0.022	0.4650	-	0.9453
30.7918	168000	0.0211	0.4592	-	0.9465
30.9751	169000	0.022	0.4727	-	0.9405
31.1584	170000	0.0184	0.4802	-	0.9460
31.3416	171000	0.0186	0.4953	-	0.9449
31.5249	172000	0.0187	0.4516	-	0.9424
31.7082	173000	0.019	0.4803	-	0.9444
31.8915	174000	0.0186	0.4499	-	0.9448
32.0748	175000	0.0181	0.5211	-	0.9377
32.2581	176000	0.0163	0.4941	-	0.9434
32.4413	177000	0.0168	0.4672	-	0.9433
32.6246	178000	0.0171	0.4990	-	0.9414
32.8079	179000	0.0185	0.4537	-	0.9444
32.9912	180000	0.0179	0.4929	-	0.9460
33.1745	181000	0.0144	0.5037	-	0.9407
33.3578	182000	0.0143	0.4986	-	0.9449
33.5411	183000	0.016	0.5043	-	0.9452
33.7243	184000	0.0152	0.5090	-	0.9427
33.9076	185000	0.0154	0.5100	-	0.9414
34.0909	186000	0.0146	0.5367	-	0.9386
34.2742	187000	0.0138	0.5063	-	0.9395
34.4575	188000	0.0143	0.4871	-	0.9446
34.6408	189000	0.014	0.4947	-	0.9483
34.824	190000	0.0142	0.5079	-	0.9467
35.0073	191000	0.014	0.5062	-	0.9439
35.1906	192000	0.0122	0.5293	-	0.9410
35.3739	193000	0.0127	0.5351	-	0.9401
35.5572	194000	0.0132	0.5263	-	0.9369
35.7405	195000	0.0134	0.5300	-	0.9427
35.9238	196000	0.0138	0.5230	-	0.9416
36.1070	197000	0.0129	0.5399	-	0.9417
36.2903	198000	0.0109	0.5352	-	0.9433
36.4736	199000	0.0114	0.5587	-	0.9404
36.6569	200000	0.012	0.5289	-	0.9441
36.8402	201000	0.012	0.5516	-	0.9434
37.0235	202000	0.0121	0.5467	-	0.9418
37.2067	203000	0.0108	0.5499	-	0.9412
37.3900	204000	0.0107	0.5459	-	0.9427
37.5733	205000	0.0105	0.5375	-	0.9414
37.7566	206000	0.0109	0.5566	-	0.9421
37.9399	207000	0.011	0.5601	-	0.9428
38.1232	208000	0.0095	0.5700	-	0.9406
38.3065	209000	0.0098	0.5493	-	0.9417
38.4897	210000	0.0093	0.5867	-	0.9372
38.6730	211000	0.0095	0.6087	-	0.9394
38.8563	212000	0.0096	0.5888	-	0.9397
39.0396	213000	0.0094	0.5806	-	0.9380
39.2229	214000	0.0087	0.5927	-	0.9393
39.4062	215000	0.0079	0.6153	-	0.9376
39.5894	216000	0.009	0.6151	-	0.9398
39.7727	217000	0.009	0.5601	-	0.9379
39.9560	218000	0.0086	0.5845	-	0.9409
40.1393	219000	0.0078	0.5929	-	0.9396
40.3226	220000	0.0077	0.6086	-	0.9417
40.5059	221000	0.0075	0.6053	-	0.9418
40.6891	222000	0.008	0.6078	-	0.9394
40.8724	223000	0.0084	0.5975	-	0.9423
41.0557	224000	0.0068	0.6410	-	0.9400
41.2390	225000	0.0067	0.6183	-	0.9409
41.4223	226000	0.0067	0.6239	-	0.9401
41.6056	227000	0.0075	0.5971	-	0.9408
41.7889	228000	0.0069	0.6458	-	0.9396
41.9721	229000	0.0073	0.6289	-	0.9337
42.1554	230000	0.0061	0.6311	-	0.9351
42.3387	231000	0.0064	0.6371	-	0.9254
42.5220	232000	0.0067	0.6119	-	0.9238
42.7053	233000	0.0068	0.6045	-	0.9435
42.8886	234000	0.0064	0.6246	-	0.9403
43.0718	235000	0.0066	0.6077	-	0.9355
43.2551	236000	0.0054	0.6348	-	0.9429
43.4384	237000	0.0053	0.6606	-	0.9414
43.6217	238000	0.0054	0.6373	-	0.9421
43.8050	239000	0.006	0.6122	-	0.9391
43.9883	240000	0.0058	0.6438	-	0.9380
44.1716	241000	0.0051	0.6474	-	0.9392
44.3548	242000	0.0049	0.6637	-	0.9399
44.5381	243000	0.005	0.6765	-	0.9420
44.7214	244000	0.0052	0.6585	-	0.9406
44.9047	245000	0.005	0.6609	-	0.9420
45.0880	246000	0.0048	0.6725	-	0.9417
45.2713	247000	0.0044	0.6597	-	0.9411
45.4545	248000	0.0045	0.6717	-	0.9381
45.6378	249000	0.0046	0.6689	-	0.9361
45.8211	250000	0.0046	0.6703	-	0.9334
46.0044	251000	0.0044	0.6958	-	0.9324
46.1877	252000	0.0041	0.6884	-	0.9380
46.3710	253000	0.0041	0.6958	-	0.9342
46.5543	254000	0.004	0.6796	-	0.9375
46.7375	255000	0.0042	0.6735	-	0.9311
46.9208	256000	0.004	0.7004	-	0.9264
47.1041	257000	0.0041	0.6798	-	0.9303
47.2874	258000	0.0036	0.7039	-	0.9330
47.4707	259000	0.0037	0.7133	-	0.9277
47.6540	260000	0.0033	0.7200	-	0.9250
47.8372	261000	0.0038	0.7204	-	0.9292
48.0205	262000	0.0034	0.7214	-	0.9336
48.2038	263000	0.0037	0.7077	-	0.9313
48.3871	264000	0.0033	0.7218	-	0.9289
48.5704	265000	0.0033	0.7258	-	0.9328
48.7537	266000	0.0034	0.7215	-	0.9346
48.9370	267000	0.0031	0.7300	-	0.9347
49.1202	268000	0.0033	0.7242	-	0.9350
49.3035	269000	0.0028	0.7320	-	0.9345
49.4868	270000	0.003	0.7397	-	0.9341
49.6701	271000	0.0029	0.7410	-	0.9342
49.8534	272000	0.0029	0.7426	-	0.9345

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.12.3
• Sentence Transformers: 5.1.0
• Transformers: 4.55.0
• PyTorch: 2.8.0+cu128
• Accelerate: 1.10.0
• Datasets: 4.0.0
• Tokenizers: 0.21.4

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",
}