Corran/SciGenNomicEmbedStatic

SentenceTransformer

This is a sentence-transformers model trained on the sci_gen_colbert_triplets dataset. 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
• Maximum Sequence Length: inf tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • sci_gen_colbert_triplets

Model Sources

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

Full Model Architecture

SentenceTransformer(
  (0): StaticEmbedding(
    (embedding): EmbeddingBag(30522, 768, mode='mean')
  )
)

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("Corran/SciGenNomicEmbedStatic")
# Run inference
sentences = [
    'Surveys and interviews: Introducing excerpts from interview data',
    "Through surveys and interviews, multiliterate teachers expressed a shared belief in the importance of fostering students' ability to navigate multiple discourse communities.",
    'The authors employ a constructivist approach to learning, where students build knowledge through active engagement with multimedia texts and collaborative discussions.',
]
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

• Dataset: SciGen-Eval-Set
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8918
cosine_accuracy@3	0.9308
cosine_accuracy@5	0.9481
cosine_accuracy@10	0.9668
cosine_precision@1	0.8918
cosine_precision@3	0.3103
cosine_precision@5	0.1896
cosine_precision@10	0.0967
cosine_recall@1	0.8918
cosine_recall@3	0.9308
cosine_recall@5	0.9481
cosine_recall@10	0.9668
cosine_ndcg@10	0.9279
cosine_mrr@10	0.9157
cosine_map@100	0.9171

Training Details

Training Dataset

sci_gen_colbert_triplets

• Dataset: sci_gen_colbert_triplets at 44071bd
• Size: 35,934 training samples
• Columns: query, positive, and negative
• Approximate statistics based on the first 1000 samples:

  	query	positive	negative
  type	string	string	string
  details	min: 20 characters mean: 50.28 characters max: 120 characters	min: 0 characters mean: 206.53 characters max: 401 characters	min: 96 characters mean: 209.67 characters max: 418 characters

• Samples:

  query	positive	negative
  Previous research: highlighting negative outcomes	Despite the widespread use of seniority-based wage systems in labor contracts, previous research has highlighted their negative outcomes, such as inefficiencies and demotivating effects on workers.	This paper, published in 1974, was among the first to establish the importance of rank-order tournaments as optimal labor contracts in microeconomics.
  Synthesising sources: contrasting evidence or ideas	Despite the observed chronic enterocolitis in Interleukin-10-deficient mice, some studies suggest that this cytokine plays a protective role in intestinal inflammation in humans (Kurimoto et al., 2001).	Chronic enterocolitis developed in Interleukin-10-deficient mice, characterized by inflammatory cell infiltration, epithelial damage, and increased production of pro-inflammatory cytokines.
  Previous research: Approaches taken	Previous research on measuring patient-relevant outcomes in osteoarthritis has primarily relied on self-reported measures, such as the Western Ontario and McMaster Universities Arthritis Index (WOMAC) (Bellamy et al., 1988).	The WOMAC (Western Ontario and McMaster Universities Osteoarthritis Index) questionnaire has been widely used in physical therapy research to assess the impact of antirheumatic drug therapy on patient-reported outcomes in individuals with hip or knee osteoarthritis.

• Loss: MatryoshkaLoss with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          768,
          384,
          256,
          128,
          64,
          32
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Evaluation Dataset

sci_gen_colbert_triplets

• Dataset: sci_gen_colbert_triplets at 44071bd
• Size: 4,492 evaluation samples
• Columns: query, positive, and negative
• Approximate statistics based on the first 1000 samples:

  	query	positive	negative
  type	string	string	string
  details	min: 20 characters mean: 50.59 characters max: 120 characters	min: 98 characters mean: 203.98 characters max: 448 characters	min: 36 characters mean: 204.82 characters max: 422 characters

• Samples:

  query	positive	negative
  Providing background information: reference to the purpose of the study	This study aimed to investigate the impact of socioeconomic status on child development, specifically focusing on cognitive, language, and social-emotional domains.	Children from high socioeconomic status families showed significantly higher IQ scores (M = 112.5, SD = 5.6) compared to children from low socioeconomic status families (M = 104.3, SD = 6.2) in the verbal IQ subtest.
  Providing background information: reference to the literature	According to previous studies using WinGX suite for small-molecule single-crystal crystallography, the optimization of crystal structures leads to improved accuracy in determining atomic coordinates.	This paper describes the WinGX suite, a powerful tool for small-molecule single-crystal crystallography that significantly advances the field of crystallography by streamlining data collection and analysis.
  General comments on the relevant literature	Polymer brushes have gained significant attention in the field of polymer science due to their unique properties, such as controlled thickness, high surface density, and tunable interfacial properties.	Despite previous reports suggesting that polymer brushes with short grafting densities exhibit poorer performance in terms of adhesion and stability compared to those with higher grafting densities (Liu et al., 2010), our results indicate that the opposite is true for certain types of polymer brushes.

• Loss: MatryoshkaLoss with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          768,
          384,
          256,
          128,
          64,
          32
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 4096
• per_device_eval_batch_size: 4096
• learning_rate: 0.02
• num_train_epochs: 50
• warmup_ratio: 0.1
• fp16: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 4096
• per_device_eval_batch_size: 4096
• 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: 0.02
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 50
• max_steps: -1
• 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: 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
• 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
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	SciGen-Eval-Set_cosine_ndcg@10
-1	-1	-	-	0.0860
1.1111	10	64.4072	61.6146	0.0919
2.2222	20	60.2737	56.0852	0.1130
3.3333	30	53.8742	50.1738	0.1611
4.4444	40	47.9741	45.6099	0.2666
5.5556	50	43.3533	42.3335	0.4579
6.6667	60	39.8746	40.0990	0.6244
7.7778	70	37.4077	38.4205	0.7223
8.8889	80	35.3558	37.0939	0.7847
10.0	90	33.5816	36.0200	0.8248
11.1111	100	32.4019	35.1148	0.8469
12.2222	110	31.3427	34.3602	0.8658
13.3333	120	30.4578	33.7324	0.8788
14.4444	130	29.7019	33.2120	0.8882
15.5556	140	29.1315	32.7679	0.8963
16.6667	150	28.6226	32.3942	0.9016
17.7778	160	28.195	32.0693	0.9061
18.8889	170	27.8242	31.7708	0.9096
20.0	180	27.373	31.5369	0.9137
21.1111	190	27.2436	31.3331	0.9168
22.2222	200	27.0084	31.1571	0.9188
23.3333	210	26.8023	31.0074	0.9205
24.4444	220	26.6754	30.8726	0.9217
25.5556	230	26.4875	30.7545	0.9224
26.6667	240	26.3846	30.6494	0.9236
27.7778	250	26.2546	30.5660	0.9243
28.8889	260	26.1752	30.4826	0.9248
30.0	270	25.9247	30.4060	0.9252
31.1111	280	25.9807	30.3540	0.9261
32.2222	290	25.9153	30.3040	0.9262
33.3333	300	25.8643	30.2585	0.9265
34.4444	310	25.7946	30.2183	0.9270
35.5556	320	25.7723	30.1799	0.9272
36.6667	330	25.7091	30.1539	0.9275
37.7778	340	25.6655	30.1296	0.9275
38.8889	350	25.6465	30.1120	0.9276
40.0	360	25.4654	30.0834	0.9279

Framework Versions

• Python: 3.11.11
• Sentence Transformers: 3.4.0
• Transformers: 4.47.1
• PyTorch: 2.5.1+cu121
• Accelerate: 1.2.1
• Datasets: 3.2.0
• Tokenizers: 0.21.0

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",
}

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}
}