metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sparse-encoder
  - sparse
  - splade
  - generated_from_trainer
  - dataset_size:90000
  - loss:SpladeLoss
  - loss:SparseMarginMSELoss
  - loss:FlopsLoss
base_model: Luyu/co-condenser-marco
widget:
  - text: weather in ljubljana, slovenia fahrenheit
  - text: which type of shark is the largest?
  - text: "Plan to have the farrier reset your horseâ\x80\x99s shoes approximately every six weeks. The shoes should be shaped to the horseâ\x80\x99s feet for a custom fit."
  - text: what oscars was kudo nominated for
  - text: "Answers from Ronald Petersen, M.D. Yes, Alzheimer's disease usually worsens slowly. But its speed of progression varies, depending on a person's genetic makeup, environmental factors, age at diagnosis and other medical conditions. Still, anyone diagnosed with Alzheimer's whose symptoms seem to be progressing quickly â\x80\x94 or who experiences a sudden decline â\x80\x94 should see his or her doctor."
pipeline_tag: feature-extraction
library_name: sentence-transformers
metrics:
  - dot_accuracy@1
  - dot_accuracy@3
  - dot_accuracy@5
  - dot_accuracy@10
  - dot_precision@1
  - dot_precision@3
  - dot_precision@5
  - dot_precision@10
  - dot_recall@1
  - dot_recall@3
  - dot_recall@5
  - dot_recall@10
  - dot_ndcg@10
  - dot_mrr@10
  - dot_map@100
  - query_active_dims
  - query_sparsity_ratio
  - corpus_active_dims
  - corpus_sparsity_ratio
co2_eq_emissions:
  emissions: 87.59304620021443
  energy_consumed: 0.2253475572552095
  source: codecarbon
  training_type: fine-tuning
  on_cloud: false
  cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
  ram_total_size: 31.777088165283203
  hours_used: 0.653
  hardware_used: 1 x NVIDIA GeForce RTX 3090
model-index:
  - name: CoCondenser trained on MS MARCO
    results:
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoMSMARCO
          type: NanoMSMARCO
        metrics:
          - type: dot_accuracy@1
            value: 0.42
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.66
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.76
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.84
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.42
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.22
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.15200000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08399999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.42
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.66
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.76
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.84
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6312406680654746
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5636904761904762
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5721212783331427
            name: Dot Map@100
          - type: query_active_dims
            value: 21.100000381469727
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9993086953547778
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 157.69065856933594
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9948335410992288
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus
          type: NanoNFCorpus
        metrics:
          - type: dot_accuracy@1
            value: 0.44
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.64
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.64
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.68
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.44
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.3933333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.336
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.27
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.04389819910134535
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.0987021139802183
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.11414854445866388
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.14007230906638554
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.34454508141466533
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5322222222222223
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.1566157643935124
            name: Dot Map@100
          - type: query_active_dims
            value: 17.920000076293945
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.999412882508476
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 311.4259948730469
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9897966714214976
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ
          type: NanoNQ
        metrics:
          - type: dot_accuracy@1
            value: 0.48
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.74
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.8
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.88
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.48
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2533333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.16799999999999998
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.09399999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.46
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.7
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.76
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.84
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6640066557351431
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6205238095238095
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.604249902859187
            name: Dot Map@100
          - type: query_active_dims
            value: 25.100000381469727
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.999177642343835
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 194.18609619140625
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9936378318527159
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-nano-beir
          name: Sparse Nano BEIR
        dataset:
          name: NanoBEIR mean
          type: NanoBEIR_mean
        metrics:
          - type: dot_accuracy@1
            value: 0.4466666666666666
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.68
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.7333333333333334
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7999999999999999
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.4466666666666666
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.28888888888888886
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.21866666666666668
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.14933333333333332
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.3079660663671151
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.4862340379934061
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.5447161814862213
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.6066907696887952
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5465974684050944
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5721455026455027
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.44432898186194736
            name: Dot Map@100
          - type: query_active_dims
            value: 21.3733336130778
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9992997400690297
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 206.63049254462427
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9932301129498518
            name: Corpus Sparsity Ratio

CoCondenser trained on MS MARCO

This is a SPLADE Sparse Encoder model finetuned from Luyu/co-condenser-marco using the sentence-transformers library. It maps sentences & paragraphs to a 30522-dimensional sparse vector space and can be used for semantic search and sparse retrieval.

Model Details

Model Description

Model Type: SPLADE Sparse Encoder
Base model: Luyu/co-condenser-marco
Maximum Sequence Length: 512 tokens
Output Dimensionality: 30522 dimensions
Similarity Function: Dot Product
Language: en
License: apache-2.0

Model Sources

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

Full Model Architecture

SparseEncoder(
  (0): MLMTransformer({'max_seq_length': 512, 'do_lower_case': False}) with MLMTransformer model: BertForMaskedLM 
  (1): SpladePooling({'pooling_strategy': 'max', 'activation_function': 'relu', 'word_embedding_dimension': 30522})
)

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 SparseEncoder

# Download from the 🤗 Hub
model = SparseEncoder("tomaarsen/splade-cocondenser-msmarco-margin-mse-minilm")
# Run inference
queries = [
    "what causes aging fast",
]
documents = [
    'UV-A light, specifically, is what mainly causes tanning, skin aging, and cataracts, UV-B causes sunburn, skin aging and skin cancer, and UV-C is the strongest, and therefore most effective at killing microorganisms. Again â\x80\x93 single words and multiple bullets.',
    "Answers from Ronald Petersen, M.D. Yes, Alzheimer's disease usually worsens slowly. But its speed of progression varies, depending on a person's genetic makeup, environmental factors, age at diagnosis and other medical conditions. Still, anyone diagnosed with Alzheimer's whose symptoms seem to be progressing quickly â\x80\x94 or who experiences a sudden decline â\x80\x94 should see his or her doctor.",
    "Bell's palsy and Extreme tiredness and Extreme fatigue (2 causes) Bell's palsy and Extreme tiredness and Hepatitis (2 causes) Bell's palsy and Extreme tiredness and Liver pain (2 causes) Bell's palsy and Extreme tiredness and Lymph node swelling in children (2 causes)",
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 30522] [3, 30522]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[11.2444, 10.6804,  4.3465]])

Evaluation

Metrics

Sparse Information Retrieval

Datasets: NanoMSMARCO, NanoNFCorpus and NanoNQ
Evaluated with SparseInformationRetrievalEvaluator

Metric	NanoMSMARCO	NanoNFCorpus	NanoNQ
dot_accuracy@1	0.42	0.44	0.48
dot_accuracy@3	0.66	0.64	0.74
dot_accuracy@5	0.76	0.64	0.8
dot_accuracy@10	0.84	0.68	0.88
dot_precision@1	0.42	0.44	0.48
dot_precision@3	0.22	0.3933	0.2533
dot_precision@5	0.152	0.336	0.168
dot_precision@10	0.084	0.27	0.094
dot_recall@1	0.42	0.0439	0.46
dot_recall@3	0.66	0.0987	0.7
dot_recall@5	0.76	0.1141	0.76
dot_recall@10	0.84	0.1401	0.84
dot_ndcg@10	0.6312	0.3445	0.664
dot_mrr@10	0.5637	0.5322	0.6205
dot_map@100	0.5721	0.1566	0.6042
query_active_dims	21.1	17.92	25.1
query_sparsity_ratio	0.9993	0.9994	0.9992
corpus_active_dims	157.6907	311.426	194.1861
corpus_sparsity_ratio	0.9948	0.9898	0.9936

Sparse Nano BEIR

Dataset: NanoBEIR_mean

Evaluated with SparseNanoBEIREvaluator with these parameters:

{
    "dataset_names": [
        "msmarco",
        "nfcorpus",
        "nq"
    ]
}

Metric	Value
dot_accuracy@1	0.4467
dot_accuracy@3	0.68
dot_accuracy@5	0.7333
dot_accuracy@10	0.8
dot_precision@1	0.4467
dot_precision@3	0.2889
dot_precision@5	0.2187
dot_precision@10	0.1493
dot_recall@1	0.308
dot_recall@3	0.4862
dot_recall@5	0.5447
dot_recall@10	0.6067
dot_ndcg@10	0.5466
dot_mrr@10	0.5721
dot_map@100	0.4443
query_active_dims	21.3733
query_sparsity_ratio	0.9993
corpus_active_dims	206.6305
corpus_sparsity_ratio	0.9932

Training Details

Training Dataset

Unnamed Dataset

Size: 90,000 training samples
Columns: query, positive, negative, and score

Approximate statistics based on the first 1000 samples:

	query	positive	negative	score
type	string	string	string	float
details	min: 4 tokens mean: 9.22 tokens max: 36 tokens	min: 15 tokens mean: 79.27 tokens max: 247 tokens	min: 16 tokens mean: 81.15 tokens max: 201 tokens	min: -14.32 mean: 4.62 max: 21.72

Samples:

query	positive	negative	score
`most powerful army in the world`	`U.S. Army Reserve Command You may be asking yourself, âWhat is the Army Reserve?â The Army is the most powerful and sophisticated military force in the world.`	`The British Royal Navy was the most powerful sea-going force by the time of World War 1 (1914-1918) and this was well-underst...`	`2.919867515563965`
`define vasomotor`	`Define peripheral neuropathy: a disease or degenerative state of the peripheral nerves in which motor, sensory, or vasomotor nerve fibers may beâ¦ a disease or degenerative state of the peripheral nerves in which motor, sensory, or vasomotor nerve fibers may be affected and which is markedâ¦`	`VairÄgya (Devanagari: à¤µà¥à¤°à¤¾à¤à¥à¤¯, also spelt Vairagya) is a Sanskrit term used in Hindu philosophy that roughly translates as dispassion, detachment, or renunciation, in particular renunciation from the pains and pleasures in the material world (Maya).`	`3.0037026405334473`
`nitrates definition biology`	`In Botany or Plant Biology. By Photosynthesis, the palisade cells make glucose which has many uses including: storage as starch, to make fat, to make cellulose and to make protein. Glucose is converted wâ¦ith mineral slat nitrates to make the protein. Nitrates provide the essential nitrogen to make protein. The Ribosome, an organelle of the plant cell, manufactures most of the cell's protein.`	Almost all inorganic nitrate salts are soluble in water at standard temperature and pressure. A common example of an inorganic nitrate salt is potassium nitrate (saltpeter). A rich source of inorganic nitrate in the human body comes from diets rich in leafy green foods, such as spinach and arugula.It is now believed that dietary nitrate in the form of plant-based foods is converted in the body to nitrite.itrate is a polyatomic ion with the molecular formula NO 3 â and a molecular mass of 62.0049 g/mol.	`-1.6804794073104858`

Loss: SpladeLoss with these parameters:

{
    "loss": "SparseMarginMSELoss",
    "lambda_corpus": 0.08,
    "lambda_query": 0.1
}

Evaluation Dataset

Unnamed Dataset

Size: 10,000 evaluation samples
Columns: query, positive, negative, and score

Approximate statistics based on the first 1000 samples:

	query	positive	negative	score
type	string	string	string	float
details	min: 4 tokens mean: 9.01 tokens max: 35 tokens	min: 17 tokens mean: 79.8 tokens max: 336 tokens	min: 18 tokens mean: 81.3 tokens max: 273 tokens	min: -15.9 mean: 4.91 max: 21.67

Samples:

query	positive	negative	score
`femoral artery definition`	`medical Definition of circumflex artery : any of several paired curving arteries: as a: either of two arteries that branch from the deep femoral artery or from the femoral artery itself:`	`Femoral vein. The femoral vein is located in the upper thigh and pelvic region of the human body. It travels in close proximity to the femoral artery. This vein is one of the larger vessels in the venous system. Instead of draining deoxygenated blood from specific parts of the body, it receives blood from several significant branches. These include popliteal, the profunda femoris, and the great sapheneous veins.`	`-0.1968388557434082`
`what causes mastitis and how do you treat it`	`Mastitis is an infection of the tissue of the breast that occurs most frequently during the time of breastfeeding. This infection causes pain, swelling, redness, and increased temperature of the breast. It can occur when bacteria, often from the infant's mouth, enter a milk duct through a crack in the nipple. This causes an infection and painful inflammation of the breast.`	`Common causes of mastitis include bacteria from the babyâs mouth, bacteria entering via breast injuries (bruising, fissures, cracks in the nipple), milk stasis (milk pooling in the breast), and bacteria from the hands of the mother or health care provider.`	`-0.8143405914306641`
`what is a buck moth`	Buck moth caterpillars that have a light background color can be confused with both the Nevada buck moth, Hemileuca nevadensis Stretch, and the New England buck moth, Hemileuca lucina Henry Edwards. The larvae of these three species can best be distinguished based on the preferred host plants (Wagner 2005).hey rely on resources that are acquired by the caterpillars (larvae). The caterpillars are robust and can exceed four inches (10 cm) in North America. Figure 4. Adult cecropia moth, Hyalophora cecropia (Linnaeus). Photograph by Pennsylvania Department of Conservation and Natural Resources-Forestry Archive, Bugwood.org.	`bucktail that gets talked about quietly in the . privacy of remote cabins. The âMusky-Teerâ is a big fish bait that anglers treasure in their collection. You wonât find these at your local bait shop but weâve been stocking these highly prized baits in all colors for years.`	`11.004357814788818`

Loss: SpladeLoss with these parameters:

{
    "loss": "SparseMarginMSELoss",
    "lambda_corpus": 0.08,
    "lambda_query": 0.1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
learning_rate: 2e-05
num_train_epochs: 1
warmup_ratio: 0.1
fp16: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
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: 1
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: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: False
fp16: True
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: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
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
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
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	NanoMSMARCO_dot_ndcg@10	NanoNFCorpus_dot_ndcg@10	NanoNQ_dot_ndcg@10	NanoBEIR_mean_dot_ndcg@10
0.0178	100	501776.8	-	-	-	-	-
0.0356	200	9740.8356	-	-	-	-	-
0.0533	300	61.9771	-	-	-	-	-
0.0711	400	37.6145	-	-	-	-	-
0.0889	500	28.8887	24.4953	0.4878	0.3047	0.5425	0.4450
0.1067	600	24.7991	-	-	-	-	-
0.1244	700	22.1517	-	-	-	-	-
0.1422	800	22.0889	-	-	-	-	-
0.16	900	20.7825	-	-	-	-	-
0.1778	1000	20.0856	18.6383	0.5751	0.3303	0.6100	0.5051
0.1956	1100	18.6968	-	-	-	-	-
0.2133	1200	20.5069	-	-	-	-	-
0.2311	1300	19.8162	-	-	-	-	-
0.2489	1400	19.1892	-	-	-	-	-
0.2667	1500	17.5024	18.0698	0.5750	0.3281	0.6222	0.5084
0.2844	1600	17.7801	-	-	-	-	-
0.3022	1700	17.9045	-	-	-	-	-
0.32	1800	16.3731	-	-	-	-	-
0.3378	1900	16.293	-	-	-	-	-
0.3556	2000	16.1167	14.5428	0.5696	0.3422	0.6232	0.5116
0.3733	2100	16.561	-	-	-	-	-
0.3911	2200	16.5533	-	-	-	-	-
0.4089	2300	14.9371	-	-	-	-	-
0.4267	2400	15.565	-	-	-	-	-
0.4444	2500	14.2143	15.2027	0.6071	0.3376	0.6600	0.5349
0.4622	2600	13.7188	-	-	-	-	-
0.48	2700	14.8554	-	-	-	-	-
0.4978	2800	15.1021	-	-	-	-	-
0.5156	2900	13.3032	-	-	-	-	-
0.5333	3000	13.8999	12.9609	0.5874	0.3423	0.6562	0.5286
0.5511	3100	12.7418	-	-	-	-	-
0.5689	3200	12.9422	-	-	-	-	-
0.5867	3300	13.6937	-	-	-	-	-
0.6044	3400	13.1183	-	-	-	-	-
0.6222	3500	12.7998	12.2024	0.6262	0.3424	0.6771	0.5486
0.64	3600	12.7799	-	-	-	-	-
0.6578	3700	12.2294	-	-	-	-	-
0.6756	3800	13.6836	-	-	-	-	-
0.6933	3900	13.579	-	-	-	-	-
0.7111	4000	12.6337	13.9878	0.6156	0.3435	0.6526	0.5372
0.7289	4100	12.682	-	-	-	-	-
0.7467	4200	12.2157	-	-	-	-	-
0.7644	4300	12.3127	-	-	-	-	-
0.7822	4400	11.7435	-	-	-	-	-
0.8	4500	12.086	12.3685	0.6262	0.3386	0.6782	0.5477
0.8178	4600	12.5455	-	-	-	-	-
0.8356	4700	11.7477	-	-	-	-	-
0.8533	4800	11.9948	-	-	-	-	-
0.8711	4900	11.8997	-	-	-	-	-
0.8889	5000	12.1624	12.8277	0.6241	0.3515	0.6740	0.5499
0.9067	5100	11.4352	-	-	-	-	-
0.9244	5200	10.9171	-	-	-	-	-
0.9422	5300	11.3242	-	-	-	-	-
0.96	5400	11.437	-	-	-	-	-
0.9778	5500	11.3141	11.6410	0.6366	0.3441	0.6605	0.5471
0.9956	5600	11.8683	-	-	-	-	-
-1	-1	-	-	0.6312	0.3445	0.6640	0.5466

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.225 kWh
Carbon Emitted: 0.088 kg of CO2
Hours Used: 0.653 hours

Training Hardware

On Cloud: No
GPU Model: 1 x NVIDIA GeForce RTX 3090
CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
RAM Size: 31.78 GB

Framework Versions

Python: 3.11.6
Sentence Transformers: 4.2.0.dev0
Transformers: 4.52.4
PyTorch: 2.6.0+cu124
Accelerate: 1.5.1
Datasets: 2.21.0
Tokenizers: 0.21.1

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",
}

SpladeLoss

@misc{formal2022distillationhardnegativesampling,
      title={From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective},
      author={Thibault Formal and Carlos Lassance and Benjamin Piwowarski and Stéphane Clinchant},
      year={2022},
      eprint={2205.04733},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2205.04733},
}

SparseMarginMSELoss

@misc{hofstätter2021improving,
    title={Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation},
    author={Sebastian Hofstätter and Sophia Althammer and Michael Schröder and Mete Sertkan and Allan Hanbury},
    year={2021},
    eprint={2010.02666},
    archivePrefix={arXiv},
    primaryClass={cs.IR}
}

FlopsLoss

@article{paria2020minimizing,
    title={Minimizing flops to learn efficient sparse representations},
    author={Paria, Biswajit and Yeh, Chih-Kuan and Yen, Ian EH and Xu, Ning and Ravikumar, Pradeep and P{'o}czos, Barnab{'a}s},
    journal={arXiv preprint arXiv:2004.05665},
    year={2020}
    }