DoDucAnh/MNLP_M2_document_encoder

SentenceTransformer based on intfloat/multilingual-e5-large-instruct

This is a sentence-transformers model finetuned from intfloat/multilingual-e5-large-instruct on the mcqa-rag-finetune dataset. It maps sentences & paragraphs to a 1024-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/multilingual-e5-large-instruct
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 1024 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • mcqa-rag-finetune

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}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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 = [
    'Hipotalamusi NUK kontrollon sekretimin e hormoneve:\nA. FSH dhe LH\nB. te rritjes(GH)\nC. ACTH\nD. te pankreasit',
    'Hipotalamusi është një pjesë e trurit që ndodhet nën talamusin. Ai luan një rol kryesor në lidhjen e sistemit nervor me sistemin endokrin përmes gjëndrës së hipofizës.',
    'State laws that regulate matters of legitimate local concern but have an incidental effect on interstate commerce are subject to a less strict balancing test. Under this test, a state law will be upheld unless the burden imposed on interstate commerce is clearly excessive in relation to the putative local benefits.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

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

Training Details

Training Dataset

mcqa-rag-finetune

• Dataset: mcqa-rag-finetune at d1f5446
• Size: 594,028 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 22 tokens mean: 105.96 tokens max: 512 tokens	min: 12 tokens mean: 70.95 tokens max: 478 tokens

• Samples:

  anchor	positive
  Find all c in Z_3 such that Z_3[x]/(x^2 + c) is a field. A. 0 B. 1 C. 2 D. 3	The notation Z_3 refers to the finite field with three elements, often denoted as {0, 1, 2}. This field operates under modular arithmetic, specifically modulo 3. Elements in Z_3 can be added and multiplied according to the rules of modulo 3, where any number can wrap around upon reaching 3.
  Find all c in Z_3 such that Z_3[x]/(x^2 + c) is a field. A. 0 B. 1 C. 2 D. 3	A field is a set equipped with two operations, addition and multiplication, satisfying certain properties: associativity, commutativity, distributivity, the existence of additive and multiplicative identities, and the existence of additive inverses and multiplicative inverses (for all elements except the zero element). In order for Z_3[x]/(f(x)) to be a field, the polynomial f(x) must be irreducible over Z_3.
  Find all c in Z_3 such that Z_3[x]/(x^2 + c) is a field. A. 0 B. 1 C. 2 D. 3	The expression Z_3[x] indicates the set of all polynomials with coefficients in Z_3. A polynomial is said to be irreducible over Z_3 if it cannot be factored into the product of two non-constant polynomials with coefficients in Z_3. In the case of quadratic polynomials like x^2 + c, irreducibility depends on whether it has any roots in the field Z_3.

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Evaluation Dataset

mcqa-rag-finetune

• Dataset: mcqa-rag-finetune at d1f5446
• Size: 1,000 evaluation samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 22 tokens mean: 98.74 tokens max: 512 tokens	min: 9 tokens mean: 59.88 tokens max: 501 tokens

• Samples:

  anchor	positive
  ക്രൂരകോഷ്ഠം ഉള്ള ഒരാളിൽ കോപിച്ചിരിക്കുന്ന ദോഷം താഴെപ്പറയുന്നവയിൽ ഏതാണ്? A. കഫം B. പിത്തം C. വാതം D. രക്തം	ഓരോ ദോഷത്തിനും അതിന്റേതായ സ്വഭാവങ്ങളും ശരീരത്തിൽ അത് ഉണ്ടാക്കുന്ന ഫലങ്ങളും ഉണ്ട്.
  Melyik tényező nem befolyásolja a fagylalt keresleti függvényét? A. A fagylalt árának változása. B. Mindegyik tényező befolyásolja. C. A jégkrém árának változása. D. A fagylalttölcsér árának változása.	A keresleti függvény negatív meredekségű, ami azt jelenti, hogy az ár növekedésével a keresett mennyiség csökken (csökkenő kereslet törvénye).
  In contrast to _______, _______ aim to reward favourable behaviour by companies. The success of such campaigns have been heightened through the use of ___________, which allow campaigns to facilitate the company in achieving _________ . A. Boycotts, Buyalls, Blockchain technology, Increased Sales B. Buycotts, Boycotts, Digital technology, Decreased Sales C. Boycotts, Buycotts, Digital technology, Decreased Sales D. Buycotts, Boycotts, Blockchain technology, Charitable donations E. Boycotts, Buyalls, Blockchain technology, Charitable donations F. Boycotts, Buycotts, Digital technology, Increased Sales G. Buycotts, Boycotts, Digital technology, Increased Sales H. Boycotts, Buycotts, Physical technology, Increased Sales I. Buycotts, Buyalls, Blockchain technology, Charitable donations J. Boycotts, Buycotts, Blockchain technology, Decreased Sales	Consumer Activism: This term refers to the actions taken by consumers to promote social, political, or environmental causes. These actions can include boycotting certain companies or buycotting others, influencing market dynamics based on ethical considerations. The effectiveness of consumer activism can vary but has gained prominence in recent years with increased visibility through social media.

• 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: 12
• per_device_eval_batch_size: 12
• learning_rate: 3e-05
• num_train_epochs: 1
• warmup_steps: 5000
• fp16: True
• load_best_model_at_end: 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: 12
• per_device_eval_batch_size: 12
• 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-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: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• warmup_steps: 5000
• 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: 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
• 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: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss
0.05	2476	0.1209	0.0347
0.1000	4952	0.0737	0.0459
0.1501	7428	0.087	0.0732
0.2001	9904	0.0825	0.1209
0.2501	12380	0.0783	0.0934
0.3001	14856	0.071	0.0793
0.3501	17332	0.0661	0.0855
0.4001	19808	0.0652	0.0964
0.4502	22284	0.063	0.0892
0.5002	24760	0.056	0.0923
0.5502	27236	0.0509	0.1016
0.6002	29712	0.045	0.0918
0.6502	32188	0.0472	0.0896
0.7002	34664	0.0396	0.0959
0.7503	37140	0.0371	0.0819
0.8003	39616	0.0341	0.0845
0.8503	42092	0.0344	0.0790
0.9003	44568	0.0288	0.0863
0.9503	47044	0.03	0.0767

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.11.9
• Sentence Transformers: 4.1.0
• Transformers: 4.52.3
• PyTorch: 2.7.0+cu126
• Accelerate: 1.7.0
• Datasets: 3.6.0
• Tokenizers: 0.21.1

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",
}

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}
}