Edit model card

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
  • Language: en
  • License: apache-2.0

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("MugheesAwan11/bge-base-scidocs-dataset-10k-2k-e1")
# Run inference
sentences = [
    'J. Appl. Phys. 111, 07E328 (2012) A single-solenoid pulsed-magnet system for single-crystal scattering studies Rev. Sci. Instrum. 83, 035101 (2012) Solution to the problem of E-cored coil above a layered half-space using the method of truncated region eigenfunction expansion J. Appl. Phys. 111, 07E717 (2012) Array of 12 coils to measure the position, alignment, and sensitivity of magnetic sensors over temperature J. Appl. Phys. 111, 07E501 (2012) Skin effect suppression for Cu/CoZrNb multilayered inductor J. Appl. Phys. 111, 07A501 (2012)',
    'which inductor can be used for multilayer scattering studies?',
    'what kind of interaction is in mobile',
]
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]

Evaluation

Metrics

Information Retrieval

Metric Value
cosine_accuracy@1 0.4995
cosine_accuracy@3 0.7685
cosine_accuracy@5 0.8205
cosine_accuracy@10 0.873
cosine_precision@1 0.4995
cosine_precision@3 0.2562
cosine_precision@5 0.1641
cosine_precision@10 0.0873
cosine_recall@1 0.4995
cosine_recall@3 0.7685
cosine_recall@5 0.8205
cosine_recall@10 0.873
cosine_ndcg@10 0.7001
cosine_ndcg@100 0.7183
cosine_mrr@10 0.6433
cosine_map@100 0.6473

Training Details

Training Dataset

Unnamed Dataset

  • Size: 10,000 training samples
  • Columns: positive and anchor
  • Approximate statistics based on the first 1000 samples:
    positive anchor
    type string string
    details
    • min: 2 tokens
    • mean: 210.86 tokens
    • max: 512 tokens
    • min: 4 tokens
    • mean: 9.51 tokens
    • max: 33 tokens
  • Samples:
    positive anchor
    This article introduces a sentiment analysis approach that adopts the way humans read, interpret, and extract sentiment from text. Our motivation builds on the assumption that human interpretation should lead to the most accurate assessment of sentiment in text. We call this automated process Human Reading for Sentiment (HRS). Previous research in sentiment analysis has produced many frameworks that can fit one or more of the HRS aspects; however, none of these methods has addressed them all in one approach. HRS provides a meta-framework for developing new sentiment analysis methods or improving existing ones. The proposed framework provides a theoretical lens for zooming in and evaluating aspects of any sentiment analysis method to identify gaps for improvements towards matching the human reading process. Key steps in HRS include the automation of humans low-level and high-level cognitive text processing. This methodology paves the way towards the integration of psychology with computational linguistics and machine learning to employ models of pragmatics and discourse analysis for sentiment analysis. HRS is tested with two state-of-the-art methods; one is based on feature engineering, and the other is based on deep learning. HRS highlighted the gaps in both methods and showed improvements for both. definition of sentiment analysis
    Although commonly used in both commercial and experimental information retrieval systems, thesauri have not demonstrated consistent beneets for retrieval performance, and it is diicult to construct a thesaurus automatically for large text databases. In this paper, an approach, called PhraseFinder, is proposed to construct collection-dependent association thesauri automatically using large full-text document collections. The association thesaurus can be accessed through natural language queries in INQUERY, an information retrieval system based on the probabilistic inference network. Experiments are conducted in IN-QUERY to evaluate diierent types of association thesauri, and thesauri constructed for a variety of collections. what is association thesaurus
    The choice of transfer functions may strongly influence complexity and performance of neural networks. Although sigmoidal transfer functions are the most common there is no a priori reason why models based on such functions should always provide optimal decision borders. A large number of alternative transfer functions has been described in the literature. A taxonomy of activation and output functions is proposed, and advantages of various non-local and local neural transfer functions are discussed. Several less-known types of transfer functions and new combinations of activation/output functions are described. Universal transfer functions, parametrized to change from localized to delocalized type, are of greatest interest. Other types of neural transfer functions discussed here include functions with activations based on nonEuclidean distance measures, bicentral functions, formed from products or linear combinations of pairs of sigmoids, and extensions of such functions making rotations of localized decision borders in highly dimensional spaces practical. Nonlinear input preprocessing techniques are briefly described, offering an alternative way to change the shapes of decision borders. types of neural transfer functions
  • Loss: MatryoshkaLoss with these parameters:
    {
        "loss": "MultipleNegativesRankingLoss",
        "matryoshka_dims": [
            768
        ],
        "matryoshka_weights": [
            1
        ],
        "n_dims_per_step": -1
    }
    

Training Hyperparameters

Non-Default Hyperparameters

  • eval_strategy: epoch
  • per_device_train_batch_size: 32
  • per_device_eval_batch_size: 16
  • learning_rate: 2e-05
  • num_train_epochs: 1
  • lr_scheduler_type: cosine
  • warmup_ratio: 0.1
  • bf16: True
  • tf32: True
  • load_best_model_at_end: True
  • optim: adamw_torch_fused
  • batch_sampler: no_duplicates

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: epoch
  • prediction_loss_only: True
  • per_device_train_batch_size: 32
  • 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
  • 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: cosine
  • 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: True
  • fp16: False
  • fp16_opt_level: O1
  • half_precision_backend: auto
  • bf16_full_eval: False
  • fp16_full_eval: False
  • tf32: True
  • 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: 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_fused
  • 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
  • batch_sampler: no_duplicates
  • multi_dataset_batch_sampler: proportional

Training Logs

Epoch Step Training Loss dim_768_cosine_map@100
0.0319 10 0.6581 -
0.0639 20 0.4842 -
0.0958 30 0.3555 -
0.1278 40 0.2398 -
0.1597 50 0.2917 -
0.1917 60 0.2286 -
0.2236 70 0.1903 -
0.2556 80 0.1832 -
0.2875 90 0.2899 -
0.3195 100 0.1744 -
0.3514 110 0.2148 -
0.3834 120 0.1379 -
0.4153 130 0.2123 -
0.4473 140 0.2445 -
0.4792 150 0.1481 -
0.5112 160 0.1392 -
0.5431 170 0.2218 -
0.5751 180 0.2225 -
0.6070 190 0.2874 -
0.6390 200 0.1927 -
0.6709 210 0.2469 -
0.7029 220 0.1915 -
0.7348 230 0.1711 -
0.7668 240 0.1982 -
0.7987 250 0.1783 -
0.8307 260 0.2016 -
0.8626 270 0.211 -
0.8946 280 0.1962 -
0.9265 290 0.1867 -
0.9585 300 0.195 -
0.9904 310 0.2161 -
1.0 313 - 0.6473
  • The bold row denotes the saved checkpoint.

Framework Versions

  • Python: 3.10.14
  • Sentence Transformers: 3.0.1
  • Transformers: 4.41.2
  • PyTorch: 2.1.2+cu121
  • Accelerate: 0.31.0
  • Datasets: 2.19.1
  • Tokenizers: 0.19.1

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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning}, 
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

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}
}
Downloads last month
3
Safetensors
Model size
109M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for MugheesAwan11/bge-base-scidocs-dataset-10k-2k-e1

Finetuned
(247)
this model

Evaluation results