Add new model.

dd3560b verified about 1 month ago

40.7 kB

language:
  - en
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:300000
  - loss:CachedMultipleNegativesRankingLoss
base_model: jhu-clsp/mmBERT-small
widget:
  - source_sentence: where is henderson mn
    sentences:
      - >-
        Confidence votes 1.7K. Assuming we're talking about the `usual' 12 volt
        car battery' the resting voltage should be around 11 to 11.5 volts.
        Under charge it's as high as 15 volts as supplied from the
        alternator,and most cars won't start if the voltage is under 10.5 to
        11.5 volts. The term `12 volt battery' is what's referred to as,
        `nominal' or `in name only' as a general reference and not meant to be
        an accurate description.
      - >-
        Henderson is a very small town of 1,000 people on the west bank of the
        Minnesota River just south of the Minneapolis and Saint Paul metro area.
      - >-
        Henderson, officially the City of Henderson, is an affluent city in
        Clark County, Nevada, United States, about 16 miles southeast of Las
        Vegas. It is the second-largest city in Nevada, after Las Vegas, with an
        estimated population of 292,969 in 2016.[2] The city is part of the Las
        Vegas metropolitan area, which spans the entire Las Vegas Valley.
        Henderson occupies the southeastern end of the valley, at an elevation
        of approximately 1,330 feet (410 m).
  - source_sentence: polytomy definition
    sentences:
      - >-
        Polytomy definition, the act or process of dividing into more than three
        parts. See more.
      - >-
        The name Loyalty has the following meaning: One who is faithful, loyal.
        It is a male name, suitable for baby boys. Origins. The name Loyalty is
        very likely a(n) English variant of the name Loyal. See other suggested
        English boy baby names. You might also like to see the other variants of
        the name Loyal.
      - "Polysemy (/pÉ\x99Ë\x88lÉªsÉªmi/ or /Ë\x88pÉ\x92lÉªsiË\x90mi/; from Greek: Ï\x80Î¿Î»Ï\N-, poly-, many and Ï\x83á¿\x86Î¼Î±, sÃªma, sign) is the capacity for a sign (such as a word, phrase, or symbol) to have multiple meanings (that is, multiple semes or sememes and thus multiple senses), usually related by contiguity of meaning within a semantic field."
  - source_sentence: age group for juvenile arthritis
    sentences:
      - "Different Types of Juvenile Rheumatoid Arthritis. There are three kinds. Each type is based on the number of joints involved, the symptoms, and certain antibodies that may be in the blood. Four or fewer joints are involved. Doctors call this pauciarticular JRA. Itâ\x80\x99s the most common form. About half of all children with juvenile rheumatoid arthritis have this type. It usually affects large joints like the knees. Girls under age 8 are most likely to get it."
      - >-
        Juvenile rheumatoid arthritis (JRA), often referred to by doctors today
        as juvenile idiopathic arthritis (JIA), is a type of arthritis that
        causes joint inflammation and stiffness for more than six weeks in a
        child aged 16 or younger. It affects approximately 50,000 children in
        the United States.
      - >-
        A depressant, or central depressant, is a drug that lowers
        neurotransmission levels, which is to depress or reduce arousal or
        stimulation, in various areas of the brain.Depressants are also
        occasionally referred to as downers as they lower the level of arousal
        when taken.istilled (concentrated) alcoholic beverages, often called 
        hard liquor , roughly eight times more alcoholic than beer. An alcoholic
        beverage is a drink that contains ethanol, an anesthetic that has been
        used as a psychoactive drug for several millennia. Ethanol is the oldest
        recreational drug still used by humans.
  - source_sentence: what is besivance and durezol used for
    sentences:
      - >-
        Besivance is antibiotic eye drops, Prolensa is antiinflammatory eye drop
        and Durezol is steroid eye drop. Besivance and Prolensa are need to be
        taken from 1-3 days prior to surgery as a prophylaxis to prevent
        postoperative infection and inflammation respectively. These eye drops
        can be administered after at least a gap of 5 minutes. They are needed
        to be administered at least 4 times per day.
      - >-
        .23 Acres Comfort, Kendall County, Texas. $399,500. This could be the
        most well known building in Comfort with excellent all around
        visibility. Constructed in the early 1930's and initially used as a bar
        it ...
      - >-
        Duloxetine is used to treat major depressive disorder and general
        anxiety disorder. Duloxetine is also used to treat fibromyalgia (a
        chronic pain disorder), or chronic muscle or joint pain (such as low
        back pain and osteoarthritis pain). Duloxetine is also used to treat
        pain caused by nerve damage in people with diabetes (diabetic
        neuropathy).
  - source_sentence: do bond funds pay dividends
    sentences:
      - >-
        If a cavity is causing the toothache, your dentist will fill the cavity
        or possibly extract the tooth, if necessary. A root canal might be
        needed if the cause of the toothache is determined to be an infection of
        the tooth's nerve. Bacteria that have worked their way into the inner
        aspects of the tooth cause such an infection. An antibiotic may be
        prescribed if there is fever or swelling of the jaw.
      - "You would have $71,200 paying out $1,687 in annual dividends. That is about $4.62 for working up in the morning. Interestingly enough, that 2.37% yield is at a low point because The Wellington Fund is a â\x80\x9Cbalanced fundâ\x80\x9D meaning that it holds a combination of stocks and bonds."
      - >-
        A bond fund or debt fund is a fund that invests in bonds, or other debt
        securities. Bond funds can be contrasted with stock funds and money
        funds. Bond funds typically pay periodic dividends that include interest
        payments on the fund's underlying securities plus periodic realized
        capital appreciation. Bond funds typically pay higher dividends than CDs
        and money market accounts. Most bond funds pay out dividends more
        frequently than individual bonds.
datasets:
  - sentence-transformers/msmarco-co-condenser-margin-mse-sym-mnrl-mean-v1
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy
co2_eq_emissions:
  emissions: 68.14048860186945
  energy_consumed: 0.2546146751831667
  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: 0.787
  hardware_used: 1 x NVIDIA GeForce RTX 3090
model-index:
  - name: SentenceTransformer based on jhu-clsp/mmBERT-small
    results:
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: msmarco co condenser eval triplet
          type: msmarco-co-condenser-eval-triplet
        metrics:
          - type: cosine_accuracy
            value: 0.6399999856948853
            name: Cosine Accuracy

SentenceTransformer based on jhu-clsp/mmBERT-small

This is a sentence-transformers model finetuned from jhu-clsp/mmBERT-small on the msmarco-co-condenser-margin-mse-sym-mnrl-mean-v1 dataset. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: jhu-clsp/mmBERT-small
Maximum Sequence Length: 8192 tokens
Output Dimensionality: 384 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- msmarco-co-condenser-margin-mse-sym-mnrl-mean-v1
Language: en

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'message_format': 'auto', 'architecture': 'ModernBertModel'})
  (1): Pooling({'embedding_dimension': 384, 'pooling_mode': 'mean', 'include_prompt': True})
)

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 SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("tomaarsen/mmBERT-small-msmarco-fa2-flattened-cmnrl")
# Run inference
sentences = [
    'do bond funds pay dividends',
    "A bond fund or debt fund is a fund that invests in bonds, or other debt securities. Bond funds can be contrasted with stock funds and money funds. Bond funds typically pay periodic dividends that include interest payments on the fund's underlying securities plus periodic realized capital appreciation. Bond funds typically pay higher dividends than CDs and money market accounts. Most bond funds pay out dividends more frequently than individual bonds.",
    'You would have $71,200 paying out $1,687 in annual dividends. That is about $4.62 for working up in the morning. Interestingly enough, that 2.37% yield is at a low point because The Wellington Fund is a â\x80\x9cbalanced fundâ\x80\x9d meaning that it holds a combination of stocks and bonds.',
    "If a cavity is causing the toothache, your dentist will fill the cavity or possibly extract the tooth, if necessary. A root canal might be needed if the cause of the toothache is determined to be an infection of the tooth's nerve. Bacteria that have worked their way into the inner aspects of the tooth cause such an infection. An antibiotic may be prescribed if there is fever or swelling of the jaw.",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [4, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[0.6686, 0.4937, 0.2202]])

Evaluation

Metrics

Triplet

Dataset: msmarco-co-condenser-eval-triplet
Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.64

Training Details

Training Dataset

msmarco-co-condenser-margin-mse-sym-mnrl-mean-v1

Dataset: msmarco-co-condenser-margin-mse-sym-mnrl-mean-v1 at 84ed2d3
Size: 300,000 training samples
Columns: query, positive, and negative

Approximate statistics based on the first 1000 samples:

	query	positive	negative
type	string	string	string
details	min: 11 characters mean: 32.46 characters max: 140 characters	min: 67 characters mean: 336.71 characters max: 864 characters	min: 56 characters mean: 339.96 characters max: 900 characters

Samples:

query	positive	negative
`what is the meaning of menu planning`	`Menu planning is the selection of a menu for an event. Such as picking out the dinner for your wedding or even a meal at a Birthday Party. Menu planning is when you are preparing a calendar of meals and you have to sit down and decide what meat and veggies you want to serve on each certain day.`	`Menu Costs. In economics, a menu cost is the cost to a firm resulting from changing its prices. The name stems from the cost of restaurants literally printing new menus, but economists use it to refer to the costs of changing nominal prices in general.`
`how old is brett butler`	`Brett Butler is 59 years old. To be more precise (and nerdy), the current age as of right now is 21564 days or (even more geeky) 517536 hours. That's a lot of hours!`	`Passed in: St. John's, Newfoundland and Labrador, Canada. Passed on: 16/07/2016. Published in the St. John's Telegram. Passed away suddenly at the Health Sciences Centre surrounded by his loving family, on July 16, 2016 Robert (Bobby) Joseph Butler, age 52 years. Predeceased by his special aunt Geri Murrin and uncle Mike Mchugh; grandparents Joe and Margaret Murrin and Jack and Theresa Butler.`
`when was the last navajo treaty sign?`	`In Executive Session, Senate of the United States, July 25, 1868. Resolved, (two-thirds of the senators present concurring,) That the Senate advise and consent to the ratification of the treaty between the United States and the Navajo Indians, concluded at Fort Sumner, New Mexico, on the first day of June, 1868.`	`Share Treaty of Greenville. The Treaty of Greenville was signed August 3, 1795, between the United States, represented by Gen. Anthony Wayne, and chiefs of the Indian tribes located in the Northwest Territory, including the Wyandots, Delawares, Shawnees, Ottawas, Miamis, and others.`

Loss: CachedMultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "mini_batch_size": 128,
    "gather_across_devices": false,
    "directions": [
        "query_to_doc"
    ],
    "partition_mode": "joint",
    "hardness_mode": null,
    "hardness_strength": 0.0
}

Evaluation Dataset

msmarco-co-condenser-margin-mse-sym-mnrl-mean-v1

Dataset: msmarco-co-condenser-margin-mse-sym-mnrl-mean-v1 at 84ed2d3
Size: 1,000 evaluation samples
Columns: query, positive, and negative

Approximate statistics based on the first 1000 samples:

	query	positive	negative
type	string	string	string
details	min: 10 characters mean: 32.61 characters max: 110 characters	min: 81 characters mean: 344.28 characters max: 908 characters	min: 97 characters mean: 342.31 characters max: 963 characters

Samples:

query	positive	negative
`what county is holly springs nc in`	`Holly Springs, North Carolina. Holly Springs is a town in Wake County, North Carolina, United States. As of the 2010 census, the town population was 24,661, over 2Â½ times its population in 2000. Contents.`	`The Mt. Holly Springs Park & Resort. One of the numerous trolley routes that carried people around the county at the turn of the century was the Carlisle & Mt. Holly Railway Company. The âHolly Trolleyâ as it came to be known was put into service by Patricio Russo and made its first run on May 14, 1901.`
`how long does nyquil stay in your system`	In order to understand exactly how long Nyquil lasts, it is absolutely vital to learn about the various ingredients in the drug. One of the ingredients found in Nyquil is Doxylamine, which is an antihistamine. This specific medication has a biological half-life or 6 to 12 hours. With this in mind, it is possible for the drug to remain in the system for a period of 12 to 24 hours. It should be known that the specifics will depend on a wide variety of different factors, including your age and metabolism.	I confirmed that NyQuil is about 10% alcohol, a higher content than most domestic beers. When I asked about the relatively high proof, I was told that the alcohol dilutes the active ingredients. The alcohol free version is there for customers with addiction issues.. also found that in that version there is twice the amount of DXM. When I asked if I could speak to a chemist or scientist, I was told they didn't have anyone who fit that description there. Itâs been eight years since I kicked NyQuil. I've been sober from alcohol for four years.
`what are mineral water`	1 Mineral water â water from a mineral spring that contains various minerals, such as salts and sulfur compounds. 2 It comes from a source tapped at one or more bore holes or spring, and originates from a geologically and physically protected underground water source. Mineral water â water from a mineral spring that contains various minerals, such as salts and sulfur compounds. 2 It comes from a source tapped at one or more bore holes or spring, and originates from a geologically and physically protected underground water source.	`Minerals for Your Body. Drinking mineral water is beneficial to health and well-being. But it is not only the amount of water you drink that is important-what the water contains is even more essential.inerals for Your Body. Drinking mineral water is beneficial to health and well-being. But it is not only the amount of water you drink that is important-what the water contains is even more essential.`

Loss: CachedMultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "mini_batch_size": 128,
    "gather_across_devices": false,
    "directions": [
        "query_to_doc"
    ],
    "partition_mode": "joint",
    "hardness_mode": null,
    "hardness_strength": 0.0
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 2048
num_train_epochs: 1
learning_rate: 8e-05
warmup_steps: 0.05
bf16: True
eval_strategy: steps
per_device_eval_batch_size: 2048
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

per_device_train_batch_size: 2048
num_train_epochs: 1
max_steps: -1
learning_rate: 8e-05
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_steps: 0.05
optim: adamw_torch_fused
optim_args: None
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
optim_target_modules: None
gradient_accumulation_steps: 1
average_tokens_across_devices: True
max_grad_norm: 1.0
label_smoothing_factor: 0.0
bf16: True
fp16: False
bf16_full_eval: False
fp16_full_eval: False
tf32: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
use_liger_kernel: False
liger_kernel_config: None
use_cache: False
neftune_noise_alpha: None
torch_empty_cache_steps: None
auto_find_batch_size: False
log_on_each_node: True
logging_nan_inf_filter: True
include_num_input_tokens_seen: no
log_level: passive
log_level_replica: warning
disable_tqdm: False
project: huggingface
trackio_space_id: trackio
eval_strategy: steps
per_device_eval_batch_size: 2048
prediction_loss_only: True
eval_on_start: False
eval_do_concat_batches: True
eval_use_gather_object: False
eval_accumulation_steps: None
include_for_metrics: []
batch_eval_metrics: False
save_only_model: False
save_on_each_node: False
enable_jit_checkpoint: False
push_to_hub: False
hub_private_repo: None
hub_model_id: None
hub_strategy: every_save
hub_always_push: False
hub_revision: None
load_best_model_at_end: False
ignore_data_skip: False
restore_callback_states_from_checkpoint: False
full_determinism: False
seed: 42
data_seed: None
use_cpu: 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
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_pin_memory: True
dataloader_persistent_workers: False
dataloader_prefetch_factor: None
remove_unused_columns: True
label_names: None
train_sampling_strategy: random
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
ddp_backend: None
ddp_timeout: 1800
fsdp: []
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
deepspeed: None
debug: []
skip_memory_metrics: True
do_predict: False
resume_from_checkpoint: None
warmup_ratio: None
local_rank: -1
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	msmarco-co-condenser-eval-triplet_cosine_accuracy
-1	-1	-	-	0.5410
0.0136	2	8.2614	-	-
0.0272	4	8.2470	-	-
0.0408	6	8.1877	-	-
0.0544	8	8.0314	-	-
0.0680	10	7.7203	-	-
0.0816	12	7.2604	-	-
0.0952	14	6.8749	-	-
0.1020	15	-	5.7117	0.6220
0.1088	16	6.5251	-	-
0.1224	18	6.1747	-	-
0.1361	20	5.8759	-	-
0.1497	22	5.5909	-	-
0.1633	24	5.3883	-	-
0.1769	26	5.1466	-	-
0.1905	28	4.8767	-	-
0.2041	30	4.6119	3.8599	0.6920
0.2177	32	4.4513	-	-
0.2313	34	4.2229	-	-
0.2449	36	3.9295	-	-
0.2585	38	3.7703	-	-
0.2721	40	3.5242	-	-
0.2857	42	3.3985	-	-
0.2993	44	3.2776	-	-
0.3061	45	-	2.5264	0.6390
0.3129	46	3.1696	-	-
0.3265	48	2.9440	-	-
0.3401	50	2.9842	-	-
0.3537	52	2.8640	-	-
0.3673	54	2.7503	-	-
0.3810	56	2.7603	-	-
0.3946	58	2.6417	-	-
0.4082	60	2.4575	2.0850	0.6370
0.4218	62	2.4319	-	-
0.4354	64	2.3469	-	-
0.4490	66	2.3213	-	-
0.4626	68	2.2758	-	-
0.4762	70	2.2147	-	-
0.4898	72	2.3848	-	-
0.5034	74	2.2504	-	-
0.5102	75	-	1.9316	0.6370
0.5170	76	2.2943	-	-
0.5306	78	2.2707	-	-
0.5442	80	2.2240	-	-
0.5578	82	2.1809	-	-
0.5714	84	2.2143	-	-
0.5850	86	2.0512	-	-
0.5986	88	2.0743	-	-
0.6122	90	2.2043	1.7521	0.6330
0.6259	92	2.1268	-	-
0.6395	94	1.9546	-	-
0.6531	96	2.0395	-	-
0.6667	98	2.0138	-	-
0.6803	100	1.9161	-	-
0.6939	102	2.0675	-	-
0.7075	104	1.9894	-	-
0.7143	105	-	1.6923	0.6420
0.7211	106	2.0513	-	-
0.7347	108	1.8997	-	-
0.7483	110	2.0753	-	-
0.7619	112	1.9403	-	-
0.7755	114	1.9421	-	-
0.7891	116	1.9446	-	-
0.8027	118	1.9905	-	-
0.8163	120	1.8458	1.6407	0.6370
0.8299	122	1.9369	-	-
0.8435	124	1.8938	-	-
0.8571	126	1.8699	-	-
0.8707	128	2.0305	-	-
0.8844	130	1.8765	-	-
0.8980	132	1.9484	-	-
0.9116	134	1.8669	-	-
0.9184	135	-	1.6204	0.6390
0.9252	136	1.9958	-	-
0.9388	138	1.9659	-	-
0.9524	140	1.8720	-	-
0.9660	142	1.9456	-	-
0.9796	144	1.8776	-	-
0.9932	146	1.9861	-	-
-1	-1	-	-	0.6400

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.255 kWh
Carbon Emitted: 0.068 kg of CO2
Hours Used: 0.787 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: 5.4.0.dev0
Transformers: 5.3.0.dev0
PyTorch: 2.10.0+cu128
Accelerate: 1.13.0.dev0
Datasets: 4.3.0
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",
}

CachedMultipleNegativesRankingLoss

@misc{gao2021scaling,
    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
    year={2021},
    eprint={2101.06983},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}