GenAIGirl's picture
Add new SentenceTransformer model.
0558cb8 verified
metadata
base_model: BAAI/bge-base-en-v1.5
datasets: []
language: []
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:1342
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: What is significant about New Delhi's history?
    sentences:
      - >-
        As of the 2011 India census, Arackal had a population of 16,739 with
        7,963 males and 8,776 females.
      - >-
        Edappadi K. Palaniswami is an Indian politician. He is the current and
        8th Chief Minister of Tamil Nadu. He is the chief minister since 16
        February 2017. Palaniswami is a senior leader of All India Anna Dravida
        Munnetra Kazhagam.
      - "New Delhi () is the capital of India and a union territory of the megacity of Delhi. It has a very old history and is home to several monuments where the city is expensive to live in. In traditional Indian geography it falls under the North Indian zone. The city has an area of about 42.7\_km. New Delhi has a population of about 9.4 Million people."
  - source_sentence: What was the significance of the Pandyan kingdom in ancient Tamil history?
    sentences:
      - >-
        Ektara (literally "one-string", also called iktar, ', yaktaro gopichand)
        is a one-string instrument. It is most often used in traditional music
        from Bangladesh, India , Egypt, and Pakistan.
      - >-
        Polygar War or Palayakarar Wars refers to the wars fought between the
        Polygars ("Palayakarrars") of former Madurai Kingdom in Tamil Nadu,
        India and the British colonial forces between March 1799 to May 1802.
        The British finally won after carrying out long and difficult protracted
        jungle campaigns against the Polygar armies and finally defeated them.
        Many lives were lost on both sides and the victory over Polygars made
        large part of territories of Tamil Nadu coming under British control
        enabling them to get a strong hold in India.
      - >-
        The Pandyan kingdom பாண்டியர் was an ancient Tamil state in South India
        of unknown antiquity. Pandyas were one of the three ancient Tamil
        kingdoms (Chola and Chera being the other two) who ruled the Tamil
        country from pre-historic times until end of the 15th century. They
        ruled initially from Korkai, a sea port on the southern most tip of the
        Indian peninsula, and in later times moved to Madurai.
  - source_sentence: Can you tell me about Louis-Frédéric Nussbaum's contributions?
    sentences:
      - >-
        Shipkila is a mountain pass and border post on the Republic of
        India-People's Republic of China border. It is through this pass which
        the river Sutlej enters India (from the Tibet Autonomous Region).
      - >-
        Suvra Mukherjee (September 17, 1940 – August 18, 2015) was the First
        Lady of India from 2012 until her death in 2015. She was the wife of
        Indian President Pranab Mukherjee from 1957 until her death in 2015.
      - >-
        Louis-Frédéric Nussbaum (1923-1996 ), also known as Louis Frédéric or
        Louis-Frédéric, was a French scholar, art historian, writer, translator
        and editor. He was a specialist in the cultures of Asia, especially
        India and Japan.
  - source_sentence: What were the original goals of Dravida Kazhagam?
    sentences:
      - >-
        Sir Patrick Geddes (2 October 1854 – 17 April 1932) was a Scottish
        biologist, sociologist, geographer, philanthropist and pioneering town
        planner. He developed a new urban theoris, including the second master
        plan of Jerusalem in 1919. He also developed the first master plan of
        Tel Aviv in 1925 that included the Bauhaus architecture in the White
        City of Tel Aviv. His other work was in India during the period of
        British India. A small memorial board to Patrick Geddes is under a
        bridge of the Heil HaShirion Street in Tel Aviv.
      - >-
        Dravida Kazhagam (or Dravidar Kazhagam, "Dravidian Organization") was
        one of the first Dravidian parties in India. The party was founded by
        E.V. Ramasamy, also called Thanthai Periyar. Its original goals were to
        eradicate the ills of the existing caste system including untouchability
        and to obtain a "Dravida Nadu" (Dravidian nation) from the Madras
        Presidency i.e., a separate nation from India for Dravidian people
        alone.
      - >-
        Dheeran Chinnamalai ( born as Theerthagiri Sarkkarai Mandraadiyaar
        [Sarkkarai Mandraadiyaar Refers Payiran Kulam] or Theerthagiri Gounder
        on April 17, 1756) was a Kongu chieftain and Palayakkarar from Tamil
        Nadu who rose up in revolt against the British East India Company in the
        Kongu Nadu, Southern India. He was born in Melapalayam, near Erode in
        the South Indian state of Tamil Nadu.
  - source_sentence: Can you tell me about the literary contributions of Chattopadhyay?
    sentences:
      - >-
        The Election Commission of India held indirect 2nd presidential
        elections of India on May 6, 1957. Dr. Rajendra Prasad won his
        re-election with 459,698 votes over his rivals Chowdhry Hari Ramwho got
        2,672 votes and Nagendra Narayan Das who got 2,000 votes. Rajendra
        Prasad, has been the only person, to have won and served two terms, as
        President of India.
      - >-
        S. Rajendra Babu (born 1 June 1939) is an Indian judge. He was the 34th
        Chief Justice of India from May to June 2004. He also served as the
        chairperson of National Human Rights Commission of India.
      - >-
        Rishi Bankim Chandra Chattopadhyay (27 June 1838 – 8 April 1894) was a
        Bengali writer, poet and journalist. He was the composer of India's
        national song "Vande Mataram". It was originally a Bengali and Sanskrit
        "stotra" (hymn) portraying India as a mother goddess. The song inspired
        the activists during the Indian Independence Movement. Chattopadhyay
        wrote 13 novels. He also wrote several 'serious, serio-comic, satirical,
        scientific and critical articles in Bengali. His works were widely
        translated into other regional languages of India.

SentenceTransformer based on BAAI/bge-base-en-v1.5

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5. It maps sentences & paragraphs to a 768-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: BAAI/bge-base-en-v1.5
  • Maximum Sequence Length: 512 tokens
  • Output Dimensionality: 768 tokens
  • Similarity Function: Cosine Similarity

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)

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("GenAIGirl/bge-base-finetune-embedder")
# Run inference
sentences = [
    'Can you tell me about the literary contributions of Chattopadhyay?',
    'Rishi Bankim Chandra Chattopadhyay (27 June 1838 – 8 April 1894) was a Bengali writer, poet and journalist. He was the composer of India\'s national song "Vande Mataram". It was originally a Bengali and Sanskrit "stotra" (hymn) portraying India as a mother goddess. The song inspired the activists during the Indian Independence Movement. Chattopadhyay wrote 13 novels. He also wrote several \'serious, serio-comic, satirical, scientific and critical articles in Bengali. His works were widely translated into other regional languages of India.',
    'S. Rajendra Babu (born 1 June 1939) is an Indian judge. He was the 34th Chief Justice of India from May to June 2004. He also served as the chairperson of National Human Rights Commission of India.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

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

Training Details

Training Dataset

Unnamed Dataset

  • Size: 1,342 training samples
  • Columns: question and context
  • Approximate statistics based on the first 1000 samples:
    question context
    type string string
    details
    • min: 6 tokens
    • mean: 12.49 tokens
    • max: 27 tokens
    • min: 9 tokens
    • mean: 83.95 tokens
    • max: 510 tokens
  • Samples:
    question context
    What is the origin of Basil? Basil ("Ocimum basilicum") ( or ) is a plant of the Family Lamiaceae. It is also known as Sweet Basil or Tulsi. It is a tender low-growing herb that is grown as a perennial in warm, tropical climates. Basil is originally native to India and other tropical regions of Asia. It has been cultivated there for more than 5,000 years. It is prominently featured in many cuisines throughout the world. Some of them are Italian, Thai, Vietnamese and Laotian cuisines. It grows to between 30–60 cm tall. It has light green, silky leaves 3–5 cm long and 1–3 cm broad. The leaves are opposite each other. The flowers are quite big. They are white in color and arranged as a spike.
    In which cuisines is Basil prominently featured? Basil ("Ocimum basilicum") ( or ) is a plant of the Family Lamiaceae. It is also known as Sweet Basil or Tulsi. It is a tender low-growing herb that is grown as a perennial in warm, tropical climates. Basil is originally native to India and other tropical regions of Asia. It has been cultivated there for more than 5,000 years. It is prominently featured in many cuisines throughout the world. Some of them are Italian, Thai, Vietnamese and Laotian cuisines. It grows to between 30–60 cm tall. It has light green, silky leaves 3–5 cm long and 1–3 cm broad. The leaves are opposite each other. The flowers are quite big. They are white in color and arranged as a spike.
    What is the significance of the Roerich Pact? The Roerich Pact is a treaty on Protection of Artistic and Scientific Institutions and Historic Monuments, signed by the representatives of 21 states in the Oval Office of the White House on 15 April 1935. As of January 1, 1990, the Roerich Pact had been ratified by ten nations: Brazil, Chile, Colombia, Cuba, the Dominican Republic, El Salvador, Guatemala, Mexico, the United States, and Venezuela. It went into effect on 26 August 1935. The Government of India approved the Treaty in 1948, but did not take any further formal action. The Roerich Pact is also known as "Pax Cultura" ("Cultural Peace" or "Peace through Culture"). The most important part of the Roerich Pact is the legal recognition that the protection of culture is always more important than any military necessity.
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
        "scale": 20.0,
        "similarity_fct": "cos_sim"
    }
    

Evaluation Dataset

Unnamed Dataset

  • Size: 100 evaluation samples
  • Columns: question and context
  • Approximate statistics based on the first 1000 samples:
    question context
    type string string
    details
    • min: 7 tokens
    • mean: 12.37 tokens
    • max: 18 tokens
    • min: 18 tokens
    • mean: 72.93 tokens
    • max: 228 tokens
  • Samples:
    question context
    What role did Suvra Mukherjee hold in India? Suvra Mukherjee (September 17, 1940 – August 18, 2015) was the First Lady of India from 2012 until her death in 2015. She was the wife of Indian President Pranab Mukherjee from 1957 until her death in 2015.
    What political party is Edappadi K. Palaniswami associated with? Edappadi K. Palaniswami is an Indian politician. He is the current and 8th Chief Minister of Tamil Nadu. He is the chief minister since 16 February 2017. Palaniswami is a senior leader of All India Anna Dravida Munnetra Kazhagam.
    Where are Tibetan antelopes primarily found? Tibetan antelope, also known as Chiru is a medium sized antelope most closely related to wild goats and sheep of the subfamily Caprinae. Tibetan antelope are native to northwest India and Tibet. They live on the treeless Steppe above . They are an endangered species. They are a target for hunters for their fine underfur called chiru. It is used to make luxury shawls. It takes about four animals to make a single shawl. In order to collect the chiru, the animals must be killed. Because of this the Chiru are close to extinction.
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
        "scale": 20.0,
        "similarity_fct": "cos_sim"
    }
    

Training Hyperparameters

Non-Default Hyperparameters

  • eval_strategy: steps
  • per_device_train_batch_size: 16
  • per_device_eval_batch_size: 16
  • learning_rate: 3e-06
  • max_steps: 166
  • 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: 3e-06
  • weight_decay: 0.0
  • adam_beta1: 0.9
  • adam_beta2: 0.999
  • adam_epsilon: 1e-08
  • max_grad_norm: 1.0
  • num_train_epochs: 3.0
  • max_steps: 166
  • 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: False
  • hub_always_push: False
  • gradient_checkpointing: False
  • gradient_checkpointing_kwargs: None
  • include_inputs_for_metrics: False
  • 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
  • dispatch_batches: None
  • split_batches: 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
  • batch_sampler: no_duplicates
  • multi_dataset_batch_sampler: proportional

Training Logs

Epoch Step Training Loss loss
0.2381 20 0.1734 0.0589
0.4762 40 0.0827 0.0477
0.7143 60 0.0737 0.0474
0.9524 80 0.0451 0.0465
1.1905 100 0.0569 0.0416
1.4286 120 0.0431 0.0407
1.6667 140 0.03 0.0406
1.9048 160 0.0389 0.0405

Framework Versions

  • Python: 3.10.12
  • Sentence Transformers: 3.0.1
  • Transformers: 4.45.1
  • PyTorch: 2.2.0+cu121
  • Accelerate: 0.34.2
  • Datasets: 2.20.0
  • Tokenizers: 0.20.0

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}
}