Qwen3-0.6B-ms-marco / README.md
chungimungi's picture
Update README.md
f1d8cb0 verified
metadata
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:17048032
  - loss:MultipleNegativesRankingLoss
base_model: Qwen/Qwen3-0.6B
widget:
  - source_sentence: is messages for android by google
    sentences:
      - >-
        Creating and Opening Files. The CreateFile function can create a new
        file or open an existing file. You must specify the file name, creation
        instructions, and other attributes. When an application creates a new
        file, the operating system adds it to the specified directory. The
        operating system assigns a unique identifier, called a handle, to each
        file that is opened or created using CreateFile. An application can use
        this handle with functions that read from, write to, and describe the
        file.
      - >-
        Google Voice gives you a free phone number for calling, text messaging,
        and voicemail. It works on smartphones and computers, and syncs across
        your devices so you can use the app while on the go or at home. You're
        in control. Forward calls, text messages, and voicemail to any of your
        devices, and get spam filtered automatically.
      - "Googleâ\x80\x99s Messenger app gets renamed â\x80\x9CAndroid Messagesâ\x80\x9D. Googleâ\x80\x99s default SMS/MMS app, Messenger, has been renamed Android Messages. The name change has just rolled out in the Play Store and arrives as Google prepares for wider adoption of the new Rich Communications Services (RCS) messaging standard."
  - source_sentence: how much does brad pitt make?
    sentences:
      - >-
        Brad Pitt net worth: Brad Pitt is an award-winning film actor and
        producer who has net worth of $240 million. Brad Pitt was raised in
        Springfield Brad Pitt net worth: Brad Pitt is an award-winning film
        actor and producer who has net worth of $240 million.
      - "An actor, Bradley Cooper is most widely recognized for â\x80¦ celebritynetworth.com Brad Pitt Net Worth-TheRichest-TheRichest-The â\x80¦ About Brad Pitt. American actor and film producer, William Bradley â\x80\x9CBradâ\x80\x9D Pitt has an estimated net worth of $240 million.With looks that have â\x80¦ therichest.com Brad Pitt Net Worth | Celebrities Net Worth 2014 Brad Pitt Net Worth. View Brad Pitt Net Worth and other Interesting and Rare Brad Pitt Facts You Won't Find Anywhere Else.radley Cooper Net Worth: Bradley Cooper is an American actor who has a net worth of $60 million dollars."
      - >-
        Lime slurry is a suspension of calcium hydroxide in water. The product
        is a user-friendly, cost-effective alkali. Lime slurry is a free-flowing
        product that is used for a variety of industrial, municipal and
        environmental applications. The product is also used extensively for the
        stabilization of expansive clay soils.
  - source_sentence: hereditary paraganglioma-pheochromocytoma syndrome
    sentences:
      - >-
        Hereditary paraganglioma-pheochromocytoma syndrome is  a condition in
        which tumors develop in structures called paraganglia. Paraganglia are
        bundles of cells of the peripheral nervous system (the nerves outside
        the brain and spinal cord). A tumor that develops in the paraganglia is
        called a paraganglioma.
      - >-
        Friendly political wager A friendly political wager is a largely
        symbolic wager made between politicians representing two cities or areas
        on the outcome of an important sports contest between teams representing
        those same two cities or areas.
      - >-
        Hereditary paraganglioma-pheochromocytoma syndrome Most cases of
        familial paraganglioma are caused by mutations in the succinate
        dehydrogenase (SDH; succinate:ubiquinone oxidoreductase) subunit genes
        (SDHD, SDHAF2, SDHC, SDHB).
  - source_sentence: what does option deposit mean in real estate
    sentences:
      - >-
        1 Option money is credited towards purchase: When you sign a Lease 2
        Purchase contract, you will pay the seller an option deposit. 2  This
        money is your vested interest in the home and will be fully (100%)
        credited to you when you buy the home. Possible sale for a profit: If
        you are allowed to sell (assign) your option (it will be in your
        agreement), you may sell it to a third party for a profit. 2  Increased
        buying power: When you buy a Lease 2 Purchase home, you can put down as
        little as first month's rent and a $1 option deposit.
      - >-
        H2 blockers reduce the amount of acid made by your stomach. They are
        used in conditions where it is helpful to reduce stomach acid. For
        example, for acid reflux which causes heartburn. Most people who take H2
        blockers do not develop any side-effects.H2 blockers are a group of
        medicines that reduce the amount of acid produced by the cells in the
        lining of the stomach. They are also called 'histamine H2-receptor
        antagonists' but are commonly called H2 blockers.They include
        cimetidine, famotidine, nizatidine and ranitidine, and have various
        different brand names. Your stomach normally produces acid to help with
        the digestion of food and to kill germs (bacteria).or example, for acid
        reflux which causes heartburn. Most people who take H2 blockers do not
        develop any side-effects. H2 blockers are a group of medicines that
        reduce the amount of acid produced by the cells in the lining of the
        stomach.
      - >-
        Option land means the person granting an option is called the optionor
        (or grantor) and the person who gets benefits of using an option is
        called optionee (or the beneficiary). An option agreement is where one
        person grants another person the exclusive right for a set time to buy a
        property normally at a set price.A non-refundable fee is normally
        charged for this option. During the term of option, no one else can buy
        or sell the property.The property may then be purchased by exercising
        option and entering into a pre-agreed form of contract or option can be
        left to expire.f you feel your property has potential for future
        development and you want to find out more, please feel free to contact
        us for free initial impartial advice without obligation. Option land for
        development as landowner grants a property developer an option for a
        fixed term of years to purchase their land.
  - source_sentence: what county is neptune city nj
    sentences:
      - >-
        Neptune City, NJ. Neptune City is a borough in Monmouth County, New
        Jersey, United States. As of the 2010 United States Census, the borough
        population was 4,869. The Borough of Neptune City was incorporated on
        October 4, 1881, based on a referendum held on March 19, 1881.
      - >-
        Neptune City, NJ. Sponsored Topics. Neptune City is a borough in
        Monmouth County, New Jersey, United States. As of the 2010 United States
        Census, the borough population was 4,869. The Borough of Neptune City
        was incorporated on October 4, 1881, based on a referendum held on March
        19, 1881.
      - >-
        There are three main types of blood cancers: Leukemia, a type of cancer
        found in your blood and bone marrow, is caused by the rapid production
        of abnormal white blood cells.yeloma is a cancer of the plasma cells.
        Plasma cells are white blood cells that produce disease-and
        infection-fighting antibodies in your body. Myeloma cells prevent the
        normal production of antibodies, leaving your body's immune system
        weakened and susceptible to infection.
pipeline_tag: sentence-similarity
library_name: sentence-transformers
datasets:
  - nixiesearch/ms-marco-hard-negatives

SentenceTransformer based on Qwen/Qwen3-0.6B

This is a sentence-transformers model finetuned from Qwen/Qwen3-0.6B. It maps sentences & paragraphs to a 1024-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: Qwen/Qwen3-0.6B
  • Maximum Sequence Length: 512 tokens
  • Output Dimensionality: 1024 dimensions
  • Similarity Function: Cosine Similarity

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: Qwen3Model 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, '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("sentence_transformers_model_id")
# Run inference
sentences = [
    'what county is neptune city nj',
    'Neptune City, NJ. Neptune City is a borough in Monmouth County, New Jersey, United States. As of the 2010 United States Census, the borough population was 4,869. The Borough of Neptune City was incorporated on October 4, 1881, based on a referendum held on March 19, 1881.',
    'Neptune City, NJ. Sponsored Topics. Neptune City is a borough in Monmouth County, New Jersey, United States. As of the 2010 United States Census, the borough population was 4,869. The Borough of Neptune City was incorporated on October 4, 1881, based on a referendum held on March 19, 1881.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Training Details

Training Dataset

Unnamed Dataset

  • Size: 17,048,032 training samples
  • Columns: sentence_0, sentence_1, and sentence_2
  • Approximate statistics based on the first 1000 samples:
    sentence_0 sentence_1 sentence_2
    type string string string
    details
    • min: 2 tokens
    • mean: 7.16 tokens
    • max: 33 tokens
    • min: 25 tokens
    • mean: 84.34 tokens
    • max: 243 tokens
    • min: 16 tokens
    • mean: 81.56 tokens
    • max: 300 tokens
  • Samples:
    sentence_0 sentence_1 sentence_2
    what county is nettles island fl Nettles Island. Nettles Island in Hutchinson Island Florida. A development of close to 1300 lots with anything from trailer pads to updated concrete block homes on a mostly man made island that juts out into the Indian River on Hutchinson Island in Saint Lucie County FL. Though, the official address for Nettles Island is in Jensen Beach. Fleming Island is an unincorporated community and census-designated place in Clay County, Florida, United States. It is located 21 miles southwest of downtown Jacksonville, on the western side of the St. Johns River, off US 17. As of the 2010 census the Fleming Island CDP had a population of 27,126. Fleming Island's ZIP code became 32003 in 2004, giving it a different code from Orange Park, the incorporated town to the north.
    what time of day to take estrogen Time of day to take Estrogen. Hi. I think we all may find different times of day are better for each of our needs. I actually feel much better using my estrogen twice a day. I use half in the morning and half in the evening. I am using a different estrogen than you and am able to split my dose. I'm glad to hear that you have been feeling very good on your current hormone therapy Hopefully just a small adjustment may be needed as our estrogen needs can change overtime. Eating fresh carrots or drinking a cup of fresh carrot juice 2-3 times a day is a wonderful way to bring on your period sooner than expected. Carrots contain high amounts of carotene, which encourages the production of estrogen. The more estrogen you have in your body, the more your period desires to arrive.
    what effects does nicotine have on your body Nicotine also activates areas of the brain that are involved in producing feelings of pleasure and reward. Recently, scientists discovered that nicotine raises the levels of a neurotransmitter called dopamine in the parts of the brain that produce feelings of pleasure and reward. The action of nicotine in the body is very complicated. It is a mild stimulant which has an effect upon the heart and brain. It stimulates the central nervous system causing irregular heartbeat and blood pressure, induces vomiting and diarrhea, and first stimulates, then inhibits glandular secretions.icotine seems to provide both a stimulant and a depressant effect, and it is likely that the effect it has at any time is determined by the mood of the user, the environment and the circumstances of use.
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
        "scale": 20.0,
        "similarity_fct": "cos_sim"
    }
    

Training Hyperparameters

Non-Default Hyperparameters

  • num_train_epochs: 1
  • max_steps: 10000
  • fp16: True
  • multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: no
  • prediction_loss_only: True
  • per_device_train_batch_size: 8
  • per_device_eval_batch_size: 8
  • 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: 5e-05
  • weight_decay: 0.0
  • adam_beta1: 0.9
  • adam_beta2: 0.999
  • adam_epsilon: 1e-08
  • max_grad_norm: 1
  • num_train_epochs: 1
  • max_steps: 10000
  • lr_scheduler_type: linear
  • lr_scheduler_kwargs: {}
  • warmup_ratio: 0.0
  • 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}
  • tp_size: 0
  • 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: batch_sampler
  • multi_dataset_batch_sampler: round_robin

Training Logs

Epoch Step Training Loss
0.0002 500 1.7342
0.0005 1000 1.7194
0.0007 1500 1.6713
0.0009 2000 1.5885
0.0012 2500 1.4152
0.0014 3000 1.3052
0.0016 3500 1.1763
0.0019 4000 1.0714
0.0021 4500 1.0235
0.0023 5000 0.9484
0.0026 5500 0.9207
0.0028 6000 0.9076
0.0031 6500 0.8736
0.0033 7000 0.8671
0.0035 7500 0.8621
0.0038 8000 0.8414
0.0040 8500 0.8228
0.0042 9000 0.8101
0.0045 9500 0.8339
0.0047 10000 0.7968

Framework Versions

  • Python: 3.10.14
  • Sentence Transformers: 4.0.1
  • Transformers: 4.51.3
  • PyTorch: 2.6.0+cu124
  • Accelerate: 1.6.0
  • Datasets: 3.2.0
  • 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",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}