sahithkumar7/final-mpnet-base-fullfinetuned-epoch2

SentenceTransformer based on microsoft/mpnet-base

This is a sentence-transformers model finetuned from microsoft/mpnet-base on the json 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
• —Base model: microsoft/mpnet-base <!-- at revision 6996ce1e91bd2a9c7d7f61daec37463394f73f09 -->
• —Maximum Sequence Length: 512 tokens
• —Output Dimensionality: 768 dimensions
• —Similarity Function: Cosine Similarity
• —Training Dataset:
• —json <!-- - Language: Unknown --> <!-- - License: Unknown -->

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': 'MPNetModel'})
  (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})
)

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("sahithkumar7/final-mpnet-base-fullfinetuned-epoch2")
# Run inference
sentences = [
    'What is the number of genes obtained from comparing control and LIPUS-stimulated samples?',
    'Differentially expressed genes (DEGs) were obtained\nbetween control and LIPUS-stimulated samples using\nan adjusted P<0.05 and|log2FC| > 1 as cutoffs to define\nstatistically significant differential expression. 676 genes\nwere obtained from which 578 were upregulated when\nstimulated with LIPUS and 98 genes were subregulated\n(Supp. Figure 1). To further understand the functions\nand pathways associated with the differentially expressed\ngenes (DEG), Gene Ontology (GO) and Kyoto Encyclo-\npedia of Genes and Genomes (KEGG) analyses were con-\nducted using the DAVID database [37, 38].',
    'independent studies have shown a raising trend in both cancer incidence [2] and a high-salt\ndietary lifestyle [7], there is no direct correlation between dietary salt intake and breast\ncancer. Interestingly, in the human body, certain organs such as the skin and lymph nodes\nhave a natural tendency to accumulate salt [8]. Although unknown, the pathophysiological\nsignificance of this selective accumulation of sodium in certain organs and solid tumors is\nan area of intense research.',
]
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, 0.6796, 0.0930],
#         [0.6796, 1.0000, 0.0629],
#         [0.0930, 0.0629, 1.0000]])

<!--

Direct Usage (Transformers)

<details><summary>Click to see the direct usage in Transformers</summary>

</details> -->

<!--

Downstream Usage (Sentence Transformers)

You can finetune this model on your own dataset.

<details><summary>Click to expand</summary>

</details> -->

<!--

Out-of-Scope Use

List how the model may foreseeably be misused and address what users ought not to do with the model. -->

Evaluation

Metrics

Triplet

• —Datasets: initial_test and final_test
• —Evaluated with <code>TripletEvaluator</code>

<!--

Bias, Risks and Limitations

What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model. -->

<!--

Recommendations

What are recommendations with respect to the foreseeable issues? For example, filtering explicit content. -->

Training Details

Training Dataset

json

• —Dataset: json
• —Size: 800 training samples
• —Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
• —Approximate statistics based on the first 800 samples: | | anchor | positive | negative | |:--------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------| | type | string | string | string | | details | <ul><li>min: 7 tokens</li><li>mean: 16.79 tokens</li><li>max: 39 tokens</li></ul> | <ul><li>min: 39 tokens</li><li>mean: 117.74 tokens</li><li>max: 265 tokens</li></ul> | <ul><li>min: 40 tokens</li><li>mean: 116.14 tokens</li><li>max: 356 tokens</li></ul> |
• —Samples: | anchor | positive | negative | |:-------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>What is the limitation of FBG-based sensors in tactile feedback?</code> | <code>Furthermore, FBG-based 3-axis tactile sensors have been<br>proposed for a more comprehensive haptic perception tool<br>in surgeries (Figure 1D) (16). Five optical fibers merged<br>with FBG sensors are suspended in a deformable medium<br>and measure the compression or tension of the tissue as the<br>sensors are pressed against it, returning a _ surface<br>reaction map. While FBG-based sensors are small, flexible, and<br>sensitive, there are several challenges that need to be<br>addressed for optimal performance for tactile feedback. These<br>sensors are temperature sensitive, requiring temperature</code> | <code>141]. Therefore, it is not known to what extent spared<br>axons are remyelinated by transplanted Schwann cells,<br>nor is the contribution of this myelin to functional im-<br>provements proven. Transplantation of Schwann cells<br>incapable of producing myelin, such as cells derived<br>from trembler (Pmp22Tr) mutant mice, may be useful<br>in establishing a causal relationship between myelin re-<br>generation and functional improvements. Several MSC<br>transplantations demonstrate an increase of myelin re-<br>tention and the number of myelinated axons in the le-<br>sion site during a chronic post-injury period [57]. Thus,</code> | | <code>What are the advantages of strain elastography?</code> | <code>frontiersin.org<br><br>--- Page 8 ---<br>Kumar et al.<br><br>TABLE 2 Modalities of ultrasound elastography.<br><br>Modality<br>Strain elastography<br><br>Excitation<br>Applied manual compression (38)<br><br>Advantages<br><br>No additional specialized equipment<br>required (40)<br><br>10.3389/fmedt.2023.1238129<br><br>Limitations<br><br>Qualitative measurements (39)<br><br>Internal physiological mechanism (42)<br><br>Simple low-cost design (40)<br><br>Applied compression is operator-dependent (51)<br><br>More commonly used (52)<br><br>High inter-observer variability (51)<br><br>coustic radiation force impulse Acoustic radiation force (43)<br><br>(ARFI) imaging<br><br>Image beyond slip boundaries (45)</code> | <code>Publisher’s Note: MDPI stays neutral<br>with regard to jurisdictional claims in<br>published maps and institutional afil-<br><br>iations.<br><br>onon)<br><br>Copyright: © 2021 by the author.<br>Licensee MDPI, Basel, Switzerland.<br>This article is an open access article<br>distributed under the terms and<br>conditions of the Creative Commons<br>Attribution (CC BY) license (https://<br>creativecommons.org/licenses/by/<br>4.0/).<br><br>Joan and Sanford I. Weill Department of Medicine, Weill Cornell Medical College, 525 East 68th Street,<br>Room M-522, Box 130, New York, NY 10065, USA; str2020@med.cornell.edu or Stefan.Ryter@proterris.com</code> | | <code>What is the material used for the substrate in a piezoelectric element?</code> | <code>gain for biomedical applications.<br><br>frontiersin.org<br><br>--- Page 9 ---<br>Kumar et al.<br><br>><br><br>[PMUT ]<br><br>Electrode: Voltage Electrode2<br><br>© piezoelectric elements<br>o<br><br>—: OSi02<br><br>©) silicon substrate<br><br>B [ CMUT ]<br>AC DC<br><br>membrane<br><br>—————<br><br>vacuum<br>insulator<br><br>substrate<br><br>= ground<br><br>FIGURE 3</code> | <code>Histopatholo<br>Cytology Total, n (%) Benign, n (%) P ey Cancer, n (%)<br>FA 2 (15.4%) FTC 2 (25%)<br>0 GD (7.7%) PTC 6 (75%)<br>I 21 (4.0%) NG 9 (69.2%)<br>Other diagnosis (7.7%)<br>FA 15 (9.9%) FIC 4 (14.3%)<br>FT-UMP (0.7%) MTC 3 (10.7%)<br>GD (0.7%) PTC 21 (75%)<br>Il 180 (34.5%) OA (0.7%)<br>LT (0.7%)<br>NG 130 (85.5%)<br>NIFTP 2 (1.3%)<br>FA 14 (23.7%) FIC 7 (28.0%)<br>FI-UMP 2 (3.4%) OTC 1 (4.0%)<br>OA (1.7%) PTC 17 (68.0%)<br>Il 84 (16.1%) LT 3 (5.1%)<br>NG 35 (59.3%)<br>NIFTP 2 (3.4%)<br>WDT-UMP 2 (3.4%)<br>FA 15 (26.3%) OTC 1 (7.7%)<br>FT-UMP 5 (8.8%) PTC 12 (92.3%)<br>OA 13 (22.8%)<br>IV 70 (13.4%) LT 2 (3.5%)<br>NG 18 (31.6%)<br>NIFTP 2 (3.5%)</code> |
• —Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }

Evaluation Dataset

json

• —Dataset: json
• —Size: 200 evaluation samples
• —Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
• —Approximate statistics based on the first 200 samples: | | anchor | positive | negative | |:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------| | type | string | string | string | | details | <ul><li>min: 7 tokens</li><li>mean: 17.14 tokens</li><li>max: 35 tokens</li></ul> | <ul><li>min: 40 tokens</li><li>mean: 121.3 tokens</li><li>max: 356 tokens</li></ul> | <ul><li>min: 45 tokens</li><li>mean: 119.75 tokens</li><li>max: 356 tokens</li></ul> |
• —Samples: | anchor | positive | negative | |:---------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>What can differentiate into a very wide variety of tissues?</code> | <code>lead to decreased rates of graft-versus-host disease. They<br>also can differentiate into a very wide variety of tissues. For<br>example, when compared with bone marrow stem cells or<br>mobilized peripheral blood, umbilical cord blood stem cells<br>have a greater repopulating ability.5° Cord blood derived<br>CD34+ cells have very potent hematopoietic abilities, and<br>this is attributed to the immaturity of the stem cells rela-<br>tive to adult derived cells. Studies have been done that an-<br>alyze long term survival of children with hematologic dis-<br>orders who were transplanted with umbilical cord blood</code> | <code>metabolic regulation may affect the function of more than one organelle. Therefore, if the<br>miR-17-92 regulatory cluster can perturb genes related to mitochondrial metabolic function,<br>it could be also related, in some way, to genes involved in lysosomal metabolic function.<br>Lysosomes are intracellular organelles that, in form of small vesicles, participate in<br>several cellular functions, mainly digestion, but also vesicle trafficking, autophagy, nutrient<br>sensing, cellular growth, signaling [85], and even enzyme secretion. The membrane-bound</code> | | <code>What are the two most common types of pluripotent stem cells?</code> | <code>III]. AMNIOTIC CELLS AS A SOURCE FOR STEM<br>CELLS<br><br>Historically, the two most common types of pluripotent<br>stem cells include embryonic stem cells (ESCs) and induced<br>pluripotent stem cells (iPSCs).35 However, despite the many<br>research efforts to improve ESC and iPSC technologies,<br>there are still enormous clinical challenges.°> Two signif-<br>icant issues posed by ESC and iPSC technologies include<br>low survival rate of transplanted cells and tumorigenicity.°><br>Recently, researchers have isolated pluripotent stem cells</code> | <code>Explanation: criterion 6 indicates a positive diagnosis only within the DC VI group<br>relative to all other categories. Criterion 5 indicates a positive diagnosis within the DCs VI<br>and V relative to all other categories.<br><br>The highest positive predictive value (PPV) confirming malignancy through histopatho-<br>logical examination for criterion 6 was 0.93, and for criterion 5, it was 0.92. For the subsequent<br>criteria, the PPVs were as follows: criterion 4—0.66; criterion 3—0.55; criterion 2—0.40.</code> | | <code>What percentage of stem cells are present in bone marrow?</code> | <code>ing 30% in some tissues.43-45 This is a significant difference<br>from the .0001-.0002% stem cells present in bone marrow.43<br>Given this difference in stem cell concentration between<br>the sources, there will be more ADSCs per sample of WAT</code> | <code>migration of bCSCs. This finding raises the possibil-<br>ity that LIPUS may decrease the ability of these cells to<br>invade adjacent tissues and start the process of metasta-<br>ses. These results also suggested that some of the changes<br>induced by LIPUS take longer to be detected in this type<br>of 2D migration model, possible due to changes in gene<br>expression pattern. To further study this hypothesis, we<br>performed a Transwell invasion assay. The data revealed<br>a reduced number of cells crossing the membrane after<br>LIPUS stimulation, indicating that therapeutic LIPUS</code> |
• —Loss: <code>MultipleNegativesRankingLoss</code> 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
• —num_train_epochs: 2
• —warmup_ratio: 0.1
• —fp16: True
• —batch_sampler: no_duplicates

All Hyperparameters

<details><summary>Click to expand</summary>

• —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: 5e-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: 2
• —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: {'minnumparams': 0, 'xla': False, 'xlafsdpv2': False, 'xlafsdpgrad_ckpt': False}
• —fsdp_transformer_layer_cls_to_wrap: None
• —accelerator_config: {'splitbatches': False, 'dispatchbatches': None, 'evenbatches': True, 'useseedablesampler': True, 'nonblocking': False, 'gradientaccumulationkwargs': 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: no_duplicates
• —multi_dataset_batch_sampler: proportional
• —router_mapping: {}
• —learning_rate_mapping: {}

</details>

Training Logs

<details><summary>Click to expand</summary>

</details>

Framework Versions

• —Python: 3.11.13
• —Sentence Transformers: 5.0.0
• —Transformers: 4.52.4
• —PyTorch: 2.6.0+cu124
• —Accelerate: 1.8.1
• —Datasets: 3.6.0
• —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",
}

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}
}

<!--

Glossary

Clearly define terms in order to be accessible across audiences. -->

<!--

Model Card Authors

Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction. -->

<!--

Model Card Contact

Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors. -->