CrossEncoder based on jhu-clsp/ettin-encoder-68m

This is a Cross Encoder model finetuned from jhu-clsp/ettin-encoder-68m on the msmarco dataset 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: jhu-clsp/ettin-encoder-68m
  • Maximum Sequence Length: 7999 tokens
  • Number of Output Labels: 1 label
  • Training Dataset:
  • Language: en

Model Sources

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("rahulseetharaman/reranker-ettin-encoder-68m-msmarco-bce-10m")
# Get scores for pairs of texts
pairs = [
    ['select committees definition government', 'There are four types of congressional committees: 1  Standing committees, which continue from one Congress to the next, are probably the most important type because they consider and shape the vast majority of proposed laws. 2  Select committees are temporarily formed for specific purposes, often to study a particular issue.'],
    ['what is a perceptual map', 'Welcome to our New Castle, Pennsylvania street map page. The street map of New Castle PA that is located below is provided by Google Maps. You can grab the New Castle Pennsylvania street map and move it around to re-centre the map. You can change between standard map view, satellite map view and hybrid map view.'],
    ['what makes your skin feel cold and burn', 'When the wind blows in cold weather, you feel colder than the actual temperature because the air blows away heat from your skin faster. For instance, if the temperature is -17.8 Celsius (0 Fahrenheit) and the wind blows at 15 mph, it feels like -28.3 Celsius (-19 Fahrenheit) -- exposed skin can freeze in 30 minutes.'],
    ['average act score for university of georgia', 'A graph of UB, University at Buffalo GPA, SAT score, and ACT score admissions data for students who were accepted, rejected, and waitlisted. A graph of UB, University at Buffalo GPA, SAT score, and ACT score admissions data for students who were accepted, rejected, and waitlisted. University at Buffalo GPA, SAT and ACT Data Search the site GO'],
    ['when was the ontario, ca, post office established', 'In 1832 Jed Jackson had the contract for carrying mail from Brantford to London twice a week along the Old Stage Road. On October 6, 1835, a post office was established at Woodstock, Ontario, with Princeton following within two years. According to the Legislative Council Sessional Papers for 1846, a post office was established at Princeton on May 6, 1836 and Jeremiah Cowin was appointed postmaster on May 9, 1837. The sureties were George Beamer and Silas Martin to the amount of £200. The assistant was John Charles.'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'select committees definition government',
    [
        'There are four types of congressional committees: 1  Standing committees, which continue from one Congress to the next, are probably the most important type because they consider and shape the vast majority of proposed laws. 2  Select committees are temporarily formed for specific purposes, often to study a particular issue.',
        'Welcome to our New Castle, Pennsylvania street map page. The street map of New Castle PA that is located below is provided by Google Maps. You can grab the New Castle Pennsylvania street map and move it around to re-centre the map. You can change between standard map view, satellite map view and hybrid map view.',
        'When the wind blows in cold weather, you feel colder than the actual temperature because the air blows away heat from your skin faster. For instance, if the temperature is -17.8 Celsius (0 Fahrenheit) and the wind blows at 15 mph, it feels like -28.3 Celsius (-19 Fahrenheit) -- exposed skin can freeze in 30 minutes.',
        'A graph of UB, University at Buffalo GPA, SAT score, and ACT score admissions data for students who were accepted, rejected, and waitlisted. A graph of UB, University at Buffalo GPA, SAT score, and ACT score admissions data for students who were accepted, rejected, and waitlisted. University at Buffalo GPA, SAT and ACT Data Search the site GO',
        'In 1832 Jed Jackson had the contract for carrying mail from Brantford to London twice a week along the Old Stage Road. On October 6, 1835, a post office was established at Woodstock, Ontario, with Princeton following within two years. According to the Legislative Council Sessional Papers for 1846, a post office was established at Princeton on May 6, 1836 and Jeremiah Cowin was appointed postmaster on May 9, 1837. The sureties were George Beamer and Silas Martin to the amount of £200. The assistant was John Charles.',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Evaluation

Metrics

Cross Encoder Reranking

  • Datasets: NanoMSMARCO_R100, NanoNFCorpus_R100 and NanoNQ_R100
  • Evaluated with CrossEncoderRerankingEvaluator with these parameters:
    {
        "at_k": 10,
        "always_rerank_positives": true
    }
    
Metric NanoMSMARCO_R100 NanoNFCorpus_R100 NanoNQ_R100
map 0.6464 (+0.1568) 0.3854 (+0.1245) 0.6581 (+0.2385)
mrr@10 0.6407 (+0.1632) 0.6487 (+0.1489) 0.6826 (+0.2559)
ndcg@10 0.7030 (+0.1626) 0.4564 (+0.1314) 0.7202 (+0.2195)

Cross Encoder Nano BEIR

  • Dataset: NanoBEIR_R100_mean
  • Evaluated with CrossEncoderNanoBEIREvaluator with these parameters:
    {
        "dataset_names": [
            "msmarco",
            "nfcorpus",
            "nq"
        ],
        "rerank_k": 100,
        "at_k": 10,
        "always_rerank_positives": true
    }
    
Metric Value
map 0.5633 (+0.1732)
mrr@10 0.6573 (+0.1893)
ndcg@10 0.6265 (+0.1711)

Training Details

Training Dataset

msmarco

  • Dataset: msmarco at 9e329ed
  • Size: 9,960,000 training samples
  • Columns: query, passage, and score
  • Approximate statistics based on the first 1000 samples:
    query passage score
    type string string float
    details
    • min: 9 characters
    • mean: 33.93 characters
    • max: 110 characters
    • min: 80 characters
    • mean: 348.08 characters
    • max: 897 characters
    • min: 0.0
    • mean: 0.49
    • max: 1.0
  • Samples:
    query passage score
    nap in chinese continued... Most children from about 21 to 36 months of age still need one nap a day, which may range from one to three and a half hours long.They typically go to bed between 7 and 9 p.m. and wake up between 6 and 8 a.m. 3-6 Years Old: 10 - 12 hours per day.ontinued... Most children from about 21 to 36 months of age still need one nap a day, which may range from one to three and a half hours long. 0.0
    what abdominal organ is most frequently injured as a result of blunt trauma? Bochdalek Hernia. Bochdalek hernia is a congenital posterolateral diaphragmatic defect that is a result of failed closure of the pleuroperitoneal ducts -- a primitive communications between the pleural and abdominal cavities -- at 8 weeks' gestation.ochdalek Hernia. Bochdalek hernia is a congenital posterolateral diaphragmatic defect that is a result of failed closure of the pleuroperitoneal ducts -- a primitive communications between the pleural and abdominal cavities -- at 8 weeks' gestation. 0.0
    where is round rock tx Driving distance from Dallas, TX to Fort Worth, TX The total driving distance from Dallas, TX to Fort Worth, TX is 33 miles or 53 kilometers. Your trip begins in Dallas, Texas. It ends in Fort Worth, Texas. If you are planning a road trip, you might also want to calculate the total driving time from Dallas, TX to Fort Worth, TX so you can see when you'll arrive at your destination. You can also calculate the cost of driving from Dallas, TX to Fort Worth, TX based on current local fuel prices and an estimate of your car's best gas mileage. 0.0
  • Loss: BinaryCrossEntropyLoss with these parameters:
    {
        "activation_fn": "torch.nn.modules.linear.Identity",
        "pos_weight": null
    }
    

Evaluation Dataset

msmarco

  • Dataset: msmarco at 9e329ed
  • Size: 40,000 evaluation samples
  • Columns: query, passage, and score
  • Approximate statistics based on the first 1000 samples:
    query passage score
    type string string float
    details
    • min: 11 characters
    • mean: 34.1 characters
    • max: 96 characters
    • min: 75 characters
    • mean: 341.31 characters
    • max: 938 characters
    • min: 0.0
    • mean: 0.49
    • max: 1.0
  • Samples:
    query passage score
    select committees definition government There are four types of congressional committees: 1 Standing committees, which continue from one Congress to the next, are probably the most important type because they consider and shape the vast majority of proposed laws. 2 Select committees are temporarily formed for specific purposes, often to study a particular issue. 1.0
    what is a perceptual map Welcome to our New Castle, Pennsylvania street map page. The street map of New Castle PA that is located below is provided by Google Maps. You can grab the New Castle Pennsylvania street map and move it around to re-centre the map. You can change between standard map view, satellite map view and hybrid map view. 0.0
    what makes your skin feel cold and burn When the wind blows in cold weather, you feel colder than the actual temperature because the air blows away heat from your skin faster. For instance, if the temperature is -17.8 Celsius (0 Fahrenheit) and the wind blows at 15 mph, it feels like -28.3 Celsius (-19 Fahrenheit) -- exposed skin can freeze in 30 minutes. 0.0
  • 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: 64
  • per_device_eval_batch_size: 64
  • learning_rate: 2e-05
  • num_train_epochs: 4
  • warmup_ratio: 0.1
  • seed: 12
  • bf16: True
  • dataloader_num_workers: 4
  • load_best_model_at_end: 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: 64
  • per_device_eval_batch_size: 64
  • 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: 4
  • 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: 12
  • data_seed: None
  • jit_mode_eval: False
  • use_ipex: False
  • bf16: True
  • 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: False
  • dataloader_num_workers: 4
  • 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: 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_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: False
  • prompts: None
  • batch_sampler: batch_sampler
  • multi_dataset_batch_sampler: proportional
  • router_mapping: {}
  • learning_rate_mapping: {}

Training Logs

Epoch Step Training Loss Validation Loss NanoMSMARCO_R100_ndcg@10 NanoNFCorpus_R100_ndcg@10 NanoNQ_R100_ndcg@10 NanoBEIR_R100_mean_ndcg@10
-1 -1 - - 0.0442 (-0.4962) 0.2555 (-0.0695) 0.0464 (-0.4542) 0.1154 (-0.3400)
0.0000 1 1.182 - - - - -
0.0643 10000 0.3736 0.1972 0.6483 (+0.1078) 0.3633 (+0.0383) 0.6880 (+0.1873) 0.5665 (+0.1112)
0.1285 20000 0.1761 0.1694 0.6341 (+0.0937) 0.4109 (+0.0858) 0.6761 (+0.1755) 0.5737 (+0.1184)
0.1928 30000 0.1552 0.1463 0.6792 (+0.1388) 0.3863 (+0.0612) 0.6831 (+0.1825) 0.5829 (+0.1275)
0.2570 40000 0.1388 0.1344 0.6949 (+0.1545) 0.4003 (+0.0753) 0.6905 (+0.1899) 0.5953 (+0.1399)
0.3213 50000 0.1297 0.1267 0.6536 (+0.1131) 0.3983 (+0.0733) 0.7293 (+0.2287) 0.5937 (+0.1384)
0.3855 60000 0.1202 0.1214 0.6771 (+0.1367) 0.3840 (+0.0589) 0.7159 (+0.2152) 0.5923 (+0.1370)
0.4498 70000 0.1124 0.1077 0.6880 (+0.1475) 0.3732 (+0.0482) 0.7256 (+0.2250) 0.5956 (+0.1402)
0.5141 80000 0.1037 0.1018 0.6684 (+0.1280) 0.3719 (+0.0469) 0.7001 (+0.1995) 0.5802 (+0.1248)
0.5783 90000 0.0956 0.0930 0.6783 (+0.1379) 0.3677 (+0.0427) 0.6870 (+0.1863) 0.5777 (+0.1223)
0.6426 100000 0.0883 0.0890 0.6971 (+0.1567) 0.4092 (+0.0842) 0.7094 (+0.2088) 0.6052 (+0.1499)
0.7068 110000 0.0839 0.0803 0.6883 (+0.1478) 0.4326 (+0.1075) 0.7181 (+0.2175) 0.6130 (+0.1576)
0.7711 120000 0.0792 0.0788 0.7013 (+0.1609) 0.4093 (+0.0843) 0.7151 (+0.2144) 0.6086 (+0.1532)
0.8353 130000 0.0755 0.0743 0.7030 (+0.1626) 0.4564 (+0.1314) 0.7202 (+0.2195) 0.6265 (+0.1711)
0.8996 140000 0.0724 0.0714 0.7014 (+0.1610) 0.3549 (+0.0299) 0.7596 (+0.2590) 0.6053 (+0.1499)
0.9639 150000 0.0688 0.0701 0.7293 (+0.1889) 0.3656 (+0.0405) 0.7116 (+0.2109) 0.6021 (+0.1468)
1.0281 160000 0.0593 0.0724 0.6591 (+0.1186) 0.3766 (+0.0515) 0.7127 (+0.2121) 0.5828 (+0.1274)
1.0924 170000 0.0514 0.0667 0.6384 (+0.0980) 0.3793 (+0.0542) 0.6664 (+0.1657) 0.5614 (+0.1060)
1.1566 180000 0.0499 0.0661 0.6643 (+0.1239) 0.3760 (+0.0510) 0.6899 (+0.1893) 0.5768 (+0.1214)
1.2209 190000 0.0479 0.0642 0.6505 (+0.1101) 0.3805 (+0.0555) 0.7143 (+0.2137) 0.5818 (+0.1264)
1.2851 200000 0.0475 0.0596 0.6545 (+0.1141) 0.3458 (+0.0208) 0.6959 (+0.1952) 0.5654 (+0.1100)
1.3494 210000 0.0459 0.0639 0.6590 (+0.1186) 0.3654 (+0.0403) 0.6613 (+0.1606) 0.5619 (+0.1065)
1.4137 220000 0.0454 0.0569 0.6402 (+0.0998) 0.3655 (+0.0405) 0.6819 (+0.1812) 0.5625 (+0.1072)
1.4779 230000 0.0446 0.0599 0.6474 (+0.1070) 0.3648 (+0.0398) 0.6731 (+0.1725) 0.5618 (+0.1064)
1.5422 240000 0.0429 0.0550 0.6416 (+0.1012) 0.3755 (+0.0505) 0.6865 (+0.1859) 0.5679 (+0.1125)
1.6064 250000 0.041 0.0563 0.6261 (+0.0857) 0.3717 (+0.0467) 0.6872 (+0.1865) 0.5617 (+0.1063)
1.6707 260000 0.04 0.0605 0.6550 (+0.1146) 0.3732 (+0.0482) 0.6900 (+0.1893) 0.5727 (+0.1174)
1.7349 270000 0.0391 0.0574 0.6292 (+0.0888) 0.3759 (+0.0508) 0.6686 (+0.1680) 0.5579 (+0.1025)
1.7992 280000 0.038 0.0519 0.6288 (+0.0884) 0.3703 (+0.0452) 0.6748 (+0.1741) 0.5580 (+0.1026)
1.8635 290000 0.0375 0.0501 0.6656 (+0.1251) 0.3793 (+0.0543) 0.7160 (+0.2154) 0.5870 (+0.1316)
1.9277 300000 0.0366 0.0472 0.6494 (+0.1090) 0.3657 (+0.0406) 0.7018 (+0.2012) 0.5723 (+0.1169)
1.9920 310000 0.0359 0.0461 0.6165 (+0.0761) 0.3812 (+0.0562) 0.6668 (+0.1661) 0.5548 (+0.0995)
2.0562 320000 0.0211 0.0598 0.5901 (+0.0497) 0.3751 (+0.0500) 0.6378 (+0.1372) 0.5343 (+0.0790)
2.1205 330000 0.02 0.0592 0.6219 (+0.0815) 0.3617 (+0.0367) 0.6317 (+0.1311) 0.5384 (+0.0831)
2.1847 340000 0.0198 0.0572 0.5953 (+0.0549) 0.3876 (+0.0626) 0.6670 (+0.1664) 0.5500 (+0.0946)
2.2490 350000 0.019 0.0605 0.5839 (+0.0435) 0.3703 (+0.0453) 0.6777 (+0.1770) 0.5440 (+0.0886)
2.3133 360000 0.0189 0.0507 0.6039 (+0.0634) 0.3756 (+0.0506) 0.6683 (+0.1677) 0.5493 (+0.0939)
2.3775 370000 0.0187 0.0522 0.6093 (+0.0688) 0.3797 (+0.0546) 0.6432 (+0.1426) 0.5441 (+0.0887)
2.4418 380000 0.0182 0.0505 0.5722 (+0.0318) 0.3674 (+0.0424) 0.6624 (+0.1618) 0.5340 (+0.0786)
2.5060 390000 0.0179 0.0448 0.5901 (+0.0497) 0.3671 (+0.0420) 0.6908 (+0.1902) 0.5493 (+0.0940)
2.5703 400000 0.0173 0.0474 0.6015 (+0.0611) 0.3500 (+0.0249) 0.6574 (+0.1567) 0.5363 (+0.0809)
2.6345 410000 0.017 0.0455 0.6096 (+0.0691) 0.3547 (+0.0296) 0.6508 (+0.1502) 0.5384 (+0.0830)
2.6988 420000 0.0168 0.0528 0.6019 (+0.0615) 0.3616 (+0.0365) 0.6860 (+0.1853) 0.5498 (+0.0944)
2.7631 430000 0.0166 0.0448 0.6017 (+0.0612) 0.3560 (+0.0310) 0.6612 (+0.1605) 0.5396 (+0.0843)
2.8273 440000 0.0152 0.0461 0.6410 (+0.1006) 0.3602 (+0.0351) 0.6418 (+0.1411) 0.5477 (+0.0923)
2.8916 450000 0.0147 0.0429 0.6335 (+0.0931) 0.3768 (+0.0517) 0.6639 (+0.1633) 0.5581 (+0.1027)
2.9558 460000 0.0148 0.0397 0.6411 (+0.1007) 0.3536 (+0.0286) 0.6693 (+0.1686) 0.5547 (+0.0993)
3.0201 470000 0.0113 0.0552 0.6431 (+0.1026) 0.3461 (+0.0211) 0.6450 (+0.1443) 0.5447 (+0.0893)
3.0843 480000 0.0051 0.0648 0.6334 (+0.0929) 0.3525 (+0.0274) 0.6761 (+0.1754) 0.5540 (+0.0986)
3.1486 490000 0.005 0.0602 0.6344 (+0.0939) 0.3519 (+0.0268) 0.6519 (+0.1513) 0.5460 (+0.0907)
3.2129 500000 0.005 0.0551 0.6287 (+0.0883) 0.3317 (+0.0067) 0.6450 (+0.1444) 0.5351 (+0.0798)
3.2771 510000 0.0047 0.0580 0.6232 (+0.0827) 0.3244 (-0.0007) 0.6508 (+0.1502) 0.5328 (+0.0774)
3.3414 520000 0.0044 0.0506 0.6047 (+0.0643) 0.3268 (+0.0017) 0.6256 (+0.1250) 0.5190 (+0.0637)
3.4056 530000 0.0044 0.0514 0.6170 (+0.0766) 0.3403 (+0.0153) 0.6354 (+0.1348) 0.5309 (+0.0755)
3.4699 540000 0.004 0.0576 0.6251 (+0.0846) 0.3388 (+0.0138) 0.6251 (+0.1245) 0.5297 (+0.0743)
3.5341 550000 0.0037 0.0487 0.6221 (+0.0817) 0.3442 (+0.0192) 0.6244 (+0.1237) 0.5302 (+0.0749)
3.5984 560000 0.0037 0.0494 0.6333 (+0.0929) 0.3371 (+0.0121) 0.6458 (+0.1451) 0.5387 (+0.0834)
3.6627 570000 0.0033 0.0426 0.6378 (+0.0974) 0.3403 (+0.0152) 0.6385 (+0.1379) 0.5389 (+0.0835)
3.7269 580000 0.0031 0.0454 0.6168 (+0.0763) 0.3473 (+0.0222) 0.6457 (+0.1451) 0.5366 (+0.0812)
3.7912 590000 0.0031 0.0434 0.6315 (+0.0911) 0.3421 (+0.0170) 0.6251 (+0.1244) 0.5329 (+0.0775)
3.8554 600000 0.0028 0.0427 0.6375 (+0.0971) 0.3406 (+0.0156) 0.6006 (+0.0999) 0.5262 (+0.0709)
3.9197 610000 0.0024 0.0397 0.6469 (+0.1065) 0.3448 (+0.0198) 0.5800 (+0.0793) 0.5239 (+0.0685)
3.9839 620000 0.0024 0.0390 0.6461 (+0.1057) 0.3473 (+0.0223) 0.5763 (+0.0757) 0.5232 (+0.0679)
-1 -1 - - 0.7030 (+0.1626) 0.4564 (+0.1314) 0.7202 (+0.2195) 0.6265 (+0.1711)
  • The bold row denotes the saved checkpoint.

Framework Versions

  • Python: 3.10.18
  • Sentence Transformers: 5.0.0
  • Transformers: 4.56.0.dev0
  • PyTorch: 2.7.1+cu126
  • Accelerate: 1.9.0
  • 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",
}
Downloads last month
6
Safetensors
Model size
68.4M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for rahulseetharaman/reranker-ettin-encoder-68m-msmarco-bce-10m

Finetuned
(5)
this model

Dataset used to train rahulseetharaman/reranker-ettin-encoder-68m-msmarco-bce-10m

Evaluation results