README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:3056
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: intfloat/e5-base-v2
widget:
  - source_sentence: >-
      Assess the strengths and weaknesses of initiatives aimed at growing
      indigenous agribusiness.
    sentences:
      - >-
        In Chile, 80% of sources go to irrigation and agriculture, making
        irrigation in agriculture a relevant element to consider. The main
        aspects associated with irrigation in agriculture are salinity,
        toxicity, and microbiological quality due to pathogenic organisms
        present in wastewater. When discussing irrigation, the type of
        irrigation must be taken into account, as there are globally two types:
        restrictive irrigation, which applies to products eaten raw, and
        irrigation without restriction, which has no significant effects on
        agriculture, animals, or humans.
      - >-
        Mr Yoshiyuki Arima discussed the World Bank's focus on sustainable
        solutions to challenges like climate change and gender equality. The
        World Bank is moving from Green Bonds to Sustainable Development Bonds,
        using SDGs as a framework. They are working with the Government Pension
        Investment Fund on research related to SDGs.
      - >-
        Technical and leadership development to grow indigenous agribusiness.
        Commercialisation and access to market channels – both domestic and
        international – for indigenous goods and services. Building networks to
        strengthen and increase participation in the food system of indigenous
        people in the Asia Pacific region.
  - source_sentence: What is the largest water-consuming sector in Australia's economy?
    sentences:
      - Navarrot holds a Minor in Sustainability Studies.
      - >-
        Australia’s agricultural sector is the largest water consuming sector in
        the economy, accounting for 65 percent of total consumption in 2005. In
        the Murray-Darling Basin, climate change will lead to decreased water
        levels and difficulties meeting demand for irrigation while maintaining
        environmental flows. Additionally, vegetation will consume more water
        under higher temperatures.
      - >-
        The project contributes to the implementation of the APEC Food Security
        Roadmap Towards 2030, focusing on food production, processing, and
        distribution. It includes targets such as improving food system related
        digital literacy, promoting public-private investment, modernizing food
        storage facilities, and sharing best practices among APEC economies.
  - source_sentence: >-
      How would you use anaerobic digestion to reduce landfill reliance in a
      city?
    sentences:
      - >-
        Innovation Approach: Technologies like anaerobic digestion and microbial
        transformation create biogas and animal feed, turning waste into
        valuable resources and reducing landfill reliance.
      - >-
        The initiative started from the previous satellite communication project
        that ITU implemented in the Pacific. ITU provided 9 economies with 93
        units of satellite ground stations, so the remote islands were connected
        with the satellites. For the islands, the satellites became essential
        communication means when disaster hits the region. For instance, when
        the hurricane hit in 2020, the satellite ground stations were the only
        communication means when the economies tried to initiate the disaster
        response efforts during the Covid lockdown. Additionally, according to
        ITU’s assessment, this communication means were used by communities and
        remote and previously unconnected communities for education and health,
        and to provide and receive government services.
      - >-
        Mexico cited changes to the lengths of growing seasons, with increased
        temperatures leading to shorter growing seasons in traditional
        agricultural areas as temperatures become too extreme for both crops and
        livestock.
  - source_sentence: What would happen if APEC economies failed to coordinate across borders?
    sentences:
      - >-
        APEC economies must co-ordinate across borders to facilitate services.
        The greater the coherence between industry and governments, the greater
        the likelihood of success.
      - >-
        Another key issue she made clear about the food systems was the
        transaction costs. To unlock the potential of the food systems, the
        transaction costs issues should be addressed. These transactions are all
        over the food systems. They are encouraged by farmers, their business
        partners to find each other, make deals and ensure that these deals are
        enforced. While the transactions being essential to the production of
        goods, the costs following them drive farmers to choose quantity over
        quality at the expense of the environment, which ultimately affect
        consumers product choices.
      - >-
        • Mortality risk: lack of real time data to react.

        • Yield optimization: no proper water quality data for yield
        optimization.
  - source_sentence: Identify the main goal of closing resource loops.
    sentences:
      - >-
        Closing resource loops aims to create new value through the reuse and
        recycling of used materials.
      - >-
        Shelf life can be extended up to 18 month, would this violate the
        expiration date?
      - >-
        Closing resource loops aims to create new value through the reuse and
        recycling of used materials.
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
model-index:
  - name: SentenceTransformer based on intfloat/e5-base-v2
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy@1
            value: 0.7447643979057592
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8992146596858639
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.93717277486911
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9607329842931938
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7447643979057592
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.32504363001745196
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.20863874345549735
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.10863874345549739
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6882635253054101
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8697643979057592
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9212478184991274
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9526614310645725
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.849824960377896
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8267877919055926
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8125610657293678
            name: Cosine Map@100

SentenceTransformer based on intfloat/e5-base-v2

This is a sentence-transformers model finetuned from intfloat/e5-base-v2. 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: intfloat/e5-base-v2
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity

Model Sources

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

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 768, '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})
  (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("sentence_transformers_model_id")
# Run inference
sentences = [
    'Identify the main goal of closing resource loops.',
    'Closing resource loops aims to create new value through the reuse and recycling of used materials.',
    'Shelf life can be extended up to 18 month, would this violate the expiration date?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.8682, 0.4450],
#         [0.8682, 1.0000, 0.4960],
#         [0.4450, 0.4960, 1.0000]])

Evaluation

Metrics

Information Retrieval

• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7448
cosine_accuracy@3	0.8992
cosine_accuracy@5	0.9372
cosine_accuracy@10	0.9607
cosine_precision@1	0.7448
cosine_precision@3	0.325
cosine_precision@5	0.2086
cosine_precision@10	0.1086
cosine_recall@1	0.6883
cosine_recall@3	0.8698
cosine_recall@5	0.9212
cosine_recall@10	0.9527
cosine_ndcg@10	0.8498
cosine_mrr@10	0.8268
cosine_map@100	0.8126

Training Details

Training Dataset

Unnamed Dataset

• Size: 3,056 training samples
• Columns: sentence_0 and sentence_1
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1
  type	string	string
  details	min: 7 tokens mean: 17.94 tokens max: 30 tokens	min: 8 tokens mean: 82.66 tokens max: 512 tokens

• Samples:

  sentence_0	sentence_1
  How does the proximity of energy generation to consumption benefit floating solar plants?	What are the benefits of using a floating solar plant? At first, the interest is the use solar energy to generate electricity. The performance peak of solar panels is at 25 degrees Celcius, anything above generates a performance loss of 0.4%. Thus, when using water as a cooling system, the photovoltaic panel stays close to 25 degrees. Another aspect to consider is the point of energy consumption, which is close to the generation point.
  Who won the Chilean award for women entrepreneurs at the regional level?	Mrs Curumilla won the Chilean award for women entrepreneurs at the regional level.
  How did the follow-up survey contribute to the establishment of working groups?	The answers and interventions collected from the survey helped establish the different working groups and address common challenges in the workshop.

• Loss: MatryoshkaLoss with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          768,
          512,
          384,
          256
      ],
      "matryoshka_weights": [
          1.0,
          0.8,
          0.6,
          0.4
      ],
      "n_dims_per_step": -1
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 6
• per_device_eval_batch_size: 6
• num_train_epochs: 4
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 6
• per_device_eval_batch_size: 6
• 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: 4
• max_steps: -1
• 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: False
• 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
• hub_revision: None
• 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
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	cosine_ndcg@10
0.7812	100	0.7980
1.0	128	0.8078
1.5625	200	0.8259
2.0	256	0.8463
2.3438	300	0.8446
3.0	384	0.8483
3.125	400	0.8498

Framework Versions

• Python: 3.10.18
• Sentence Transformers: 5.0.0
• Transformers: 4.53.1
• PyTorch: 2.6.0+cu124
• Accelerate: 1.8.1
• Datasets: 2.14.0
• Tokenizers: 0.21.2

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",
}

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}
}