shahdAI's picture
Upload folder using huggingface_hub
417a112 verified
|
Raw
History Blame Contribute Delete
17.6 kB
metadata
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:131044
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: Omartificial-Intelligence-Space/Arabic-Triplet-Matryoshka-V2
widget:
  - source_sentence: >-
      ู…ุงู‡ูŠ ุงู„ูƒู„ู…ู‡ ุงู„ุชูŠ ุชุนู†ูŠ: ุนู…ู„ู‡ ูŠุชู… ุชุฏุงูˆู„ู‡ุง ุจูŠู† ู…ุฌู…ูˆุนู‡ ู…ู† ุงู„ุฏูˆู„ ุงู„ู…ุชุญุงู„ูู‡
      ุงู‚ุชุตุงุฏูŠุง ุจุฏู„ุง ู…ู† ุนู…ู„ุงุชู‡ุง ุงู„ู…ุญู„ูŠู‡.
    sentences:
      - 'ุฑุฌุญุงู†ุŒ ูˆุชุฑุฌู…ุชู‡ุง: appropriateุŒ ูˆู‚ุณู…ู‡ุง ุงู„ูƒู„ุงู…ูŠ: ุงุณู… ู…ุนู†ู‰'
      - ู…ุญูŠุง
      - ุงู„ุนู…ู„ู‡ ุงู„ู…ูˆุญุฏู‡
  - source_sentence: 'ู…ุงู‡ูŠ ุงู„ูƒู„ู…ู‡ ุงู„ุชูŠ ุชุนู†ูŠ: ุชุทุงุจู‚ ุงู„ู„ูุธูŠู† ุงูˆ ุชุดุงุจู‡ู‡ู…ุง ููŠ ุงู„ู…ุนู†ู‰.'
    sentences:
      - 'ุชุฑุงุฏูุŒ ูˆุชุฑุฌู…ุชู‡ุง: synonymityุŒ ูˆู‚ุณู…ู‡ุง ุงู„ูƒู„ุงู…ูŠ: ุงุณู… ู…ุนู†ู‰'
      - ุชุงุจู†
      - 'ุดุญุฐุŒ ูˆุชุฑุฌู…ุชู‡ุง: To whetุŒ ูˆู‚ุณู…ู‡ุง ุงู„ูƒู„ุงู…ูŠ: ูุนู„ ู…ุชุนุฏูŠ'
  - source_sentence: 'ู…ุงู‡ูŠ ุงู„ูƒู„ู…ู‡ ุงู„ุชูŠ ุชุนู†ูŠ: ู…ุตุทู„ุญ ุนู„ู‰ ุฑู…ุฒ ุงู„ุทุฑุญ ููŠ ุงู„ุญุณุงุจ.'
    sentences:
      - 'ู†ุงู‚ุตุŒ ูˆู‚ุณู…ู‡ุง ุงู„ูƒู„ุงู…ูŠ: ุงุณู… ุฐุงุช'
      - ู…ู„ุบูˆุจ ููŠ
      - 'ุงุณุชุนุงุฑู‡ุŒ ูˆุชุฑุฌู…ุชู‡ุง: borrowingุŒ ูˆู‚ุณู…ู‡ุง ุงู„ูƒู„ุงู…ูŠ: ุงุณู… ู…ุนู†ู‰'
  - source_sentence: 'ู…ุงู‡ูŠ ุงู„ูƒู„ู…ู‡ ุงู„ุชูŠ ุชุนู†ูŠ: ุชูˆุซูŠู‚ุŒ ูˆุงุญูƒุงู….'
    sentences:
      - ุชู„ุงุญู…
      - >-
        ู…ุชูู‚ุŒ ูˆู…ุซุงู„ ุงู„ูƒู„ู…ู‡ ู‡ูˆ: ู…ู†ุฐ ุงู„ุจุฏุงูŠู‡ ุงู‚ูˆู„ ุจุงู†ูŠ (ู…ุชูู‚) ู…ุนู‡ ููŠ ู…ุนุธู… ู…ุง
        ู‚ุงู„ู‡.ุŒ ูˆุชุฑุฌู…ุชู‡ุง: Agreeing withุŒ ูˆู‚ุณู…ู‡ุง ุงู„ูƒู„ุงู…ูŠ: ุตูู‡ ูุงุนู„
      - ุชูˆูƒูŠุฏ
  - source_sentence: >-
      ู…ุงู‡ูŠ ุงู„ูƒู„ู…ู‡ ุงู„ุชูŠ ุชุนู†ูŠ: ุชุญุฒู… ุจุงู„ุซูˆุจ ูˆุดุฏู‡ ุชู‡ูŠุคุง ู„ุงู…ุฑ ูˆุงุณุชุนุฏุงุฏุง ู„ู‡ุŒ ุงูˆ ุฌุฐุจ
      ุดุฎุต ู…ู† ุซูŠุงุจู‡ ุงู„ุชูŠ ุนู†ุฏ ุนู†ู‚ู‡
    sentences:
      - ุชุญุดูŠู‡
      - ุงู†ุฐุฑ
      - ุชู„ุจุจ
pipeline_tag: sentence-similarity
library_name: sentence-transformers

SentenceTransformer based on Omartificial-Intelligence-Space/Arabic-Triplet-Matryoshka-V2

This is a sentence-transformers model finetuned from Omartificial-Intelligence-Space/Arabic-Triplet-Matryoshka-V2. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'mean', '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 ๐Ÿค— Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    'ู…ุงู‡ูŠ ุงู„ูƒู„ู…ู‡ ุงู„ุชูŠ ุชุนู†ูŠ: ุชุญุฒู… ุจุงู„ุซูˆุจ ูˆุดุฏู‡ ุชู‡ูŠุคุง ู„ุงู…ุฑ ูˆุงุณุชุนุฏุงุฏุง ู„ู‡ุŒ ุงูˆ ุฌุฐุจ ุดุฎุต ู…ู† ุซูŠุงุจู‡ ุงู„ุชูŠ ุนู†ุฏ ุนู†ู‚ู‡',
    'ุชู„ุจุจ',
    'ุชุญุดูŠู‡',
]
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,  0.4581,  0.1173],
#         [ 0.4581,  1.0000, -0.0107],
#         [ 0.1173, -0.0107,  1.0000]])

Training Details

Training Dataset

Unnamed Dataset

  • Size: 131,044 training samples
  • Columns: anchor, positive, and negative
  • Approximate statistics based on the first 1000 samples:
    anchor positive negative
    type string string string
    details
    • min: 9 tokens
    • mean: 17.41 tokens
    • max: 54 tokens
    • min: 3 tokens
    • mean: 15.64 tokens
    • max: 73 tokens
    • min: 3 tokens
    • mean: 3.97 tokens
    • max: 9 tokens
  • Samples:
    anchor positive negative
    ู…ุงู‡ูŠ ุงู„ูƒู„ู…ู‡ ุงู„ุชูŠ ุชุนู†ูŠ: ูุชุฑ ูู„ุงู† ู‡ู…ู‡ ูู„ุงู†: ุงุถุนูู‡ุง. ูุชุฑ ู‡ุชู
    ู…ุงู‡ูŠ ุงู„ูƒู„ู…ู‡ ุงู„ุชูŠ ุชุนู†ูŠ: ุนุงุตู…ู‡ ุงูŠุฑู„ู†ุฏุงุŒ ุชู‚ุน ู‚ุฑุจ ู…ู†ุชุตู ุงู„ุณุงุญู„ ุงู„ุดุฑู‚ูŠ ุงู„ุงูŠุฑู„ู†ุฏูŠุŒ ุนู†ุฏ ู…ุตุจ ู†ู‡ุฑ ู„ูŠููŠุŒ ูˆุชู‚ุฏุฑ ู…ุณุงุญุชู‡ุง ุจู†ุญูˆ 117.8 ูƒูŠู„ูˆ ู…ุชุฑ ู…ุฑุจุนุง. ุฏุจู„ู†ุŒ ูˆุชุฑุฌู…ุชู‡ุง: DublinุŒ ูˆู‚ุณู…ู‡ุง ุงู„ูƒู„ุงู…ูŠ: ุงุณู… ุฐุงุช ูˆุงุดู†ุทู†
    ู…ุงู‡ูŠ ุงู„ูƒู„ู…ู‡ ุงู„ุชูŠ ุชุนู†ูŠ: ุงู„ู†ุธุงู… ุงู„ุฐูŠ ูŠูƒูˆู† ููŠู‡ ุงู„ุงู‚ุชุฑุงู† ุงู„ุฐูŠ ูŠุฎุชู„ู ุนู† ุงู‚ุชุฑุงู† ุงู„ู…ุนุงุฏู„ู‡ ุงู„ุงุตู„ูŠ ู„ุง ูŠุณุงูˆูŠ ุตูุฑุง ุณูˆุงุก ุงูƒุงู†ุช ุงู„ู…ุนุงุฏู„ู‡ ู…ู† ุงู„ุฑุชุจู‡ ุงู„ุงูˆู„ู‰ ุงูˆ ุงู„ุซุงู†ูŠู‡. ู…ุนุงุฏู„ู‡ ุบูŠุฑ ู…ุชุฌุงู†ุณู‡ ุณูŠุงุณู‡ ุงู„ุงุณุชุฎุฏุงู… ุงู„ุนุงุฏู„
  • Loss: MatryoshkaLoss with these parameters:
    {
        "loss": "MultipleNegativesRankingLoss",
        "matryoshka_dims": [
            768
        ],
        "matryoshka_weights": [
            1
        ],
        "n_dims_per_step": -1
    }
    

Evaluation Dataset

Unnamed Dataset

  • Size: 14,561 evaluation samples
  • Columns: anchor, positive, and negative
  • Approximate statistics based on the first 1000 samples:
    anchor positive negative
    type string string string
    details
    • min: 9 tokens
    • mean: 17.36 tokens
    • max: 52 tokens
    • min: 3 tokens
    • mean: 15.68 tokens
    • max: 313 tokens
    • min: 3 tokens
    • mean: 3.97 tokens
    • max: 9 tokens
  • Samples:
    anchor positive negative
    ู…ุงู‡ูŠ ุงู„ูƒู„ู…ู‡ ุงู„ุชูŠ ุชุนู†ูŠ: ู…ุคู†ุซ (ุฑุฎูˆ) ุฑุฎูˆู‡ุŒ ูˆู‚ุณู…ู‡ุง ุงู„ูƒู„ุงู…ูŠ: ุตูู‡ ู…ุดุจู‡ู‡ ุฑุฎูˆูŠู‡
    ู…ุงู‡ูŠ ุงู„ูƒู„ู…ู‡ ุงู„ุชูŠ ุชุนู†ูŠ: ู…ุฒุฎุฑู ูˆู…ุฑุตุน ู…ุจุฑู‚ุด ู…ุฎุงู
    ู…ุงู‡ูŠ ุงู„ูƒู„ู…ู‡ ุงู„ุชูŠ ุชุนู†ูŠ: ู…ูƒุชุณุจ ุญุฑุงู… ูˆุบูŠุฑ ู…ุดุฑูˆุน ู…ู† ู…ุงู„ ูˆู†ุญูˆู‡ ู…ุณุญุชุŒ ูˆู…ุซุงู„ ุงู„ูƒู„ู…ู‡ ู‡ูˆ: ูุงู†ู‡ ูŠุถู…ุฑ ููŠ ุงู„ู…ุณุญุช ูˆุงู„ู…ุฌู„ู ู…ุง ูŠุฑูุนู‡ ู…ุซู„ ุงู„ุฐูŠ ูˆู†ุญูˆู‡ุŒุŒ ูˆู‚ุณู…ู‡ุง ุงู„ูƒู„ุงู…ูŠ: ุตูู‡ ู…ูุนูˆู„ ู…ุณุญูˆุช
  • Loss: MatryoshkaLoss with these parameters:
    {
        "loss": "MultipleNegativesRankingLoss",
        "matryoshka_dims": [
            768
        ],
        "matryoshka_weights": [
            1
        ],
        "n_dims_per_step": -1
    }
    

Training Hyperparameters

Non-Default Hyperparameters

  • per_device_train_batch_size: 512
  • per_device_eval_batch_size: 512
  • num_train_epochs: 5
  • warmup_steps: 0.1
  • fp16: True
  • batch_sampler: no_duplicates

All Hyperparameters

Click to expand
  • do_predict: False
  • prediction_loss_only: True
  • per_device_train_batch_size: 512
  • per_device_eval_batch_size: 512
  • 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: 5
  • max_steps: -1
  • lr_scheduler_type: linear
  • lr_scheduler_kwargs: None
  • warmup_ratio: None
  • warmup_steps: 0.1
  • log_level: passive
  • log_level_replica: warning
  • log_on_each_node: True
  • logging_nan_inf_filter: True
  • enable_jit_checkpoint: False
  • save_on_each_node: False
  • save_only_model: False
  • restore_callback_states_from_checkpoint: False
  • use_cpu: False
  • seed: 42
  • data_seed: None
  • bf16: False
  • fp16: True
  • bf16_full_eval: False
  • fp16_full_eval: False
  • tf32: None
  • local_rank: -1
  • ddp_backend: None
  • debug: []
  • dataloader_drop_last: False
  • dataloader_num_workers: 0
  • dataloader_prefetch_factor: None
  • disable_tqdm: False
  • remove_unused_columns: True
  • label_names: None
  • load_best_model_at_end: False
  • ignore_data_skip: False
  • fsdp: []
  • fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
  • accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
  • parallelism_config: None
  • deepspeed: None
  • label_smoothing_factor: 0.0
  • optim: adamw_torch_fused
  • optim_args: None
  • group_by_length: False
  • length_column_name: length
  • project: huggingface
  • trackio_space_id: trackio
  • 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
  • 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_for_metrics: []
  • eval_do_concat_batches: True
  • auto_find_batch_size: False
  • full_determinism: False
  • ddp_timeout: 1800
  • torch_compile: False
  • torch_compile_backend: None
  • torch_compile_mode: None
  • include_num_input_tokens_seen: no
  • 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: True
  • use_cache: False
  • prompts: None
  • batch_sampler: no_duplicates
  • multi_dataset_batch_sampler: proportional
  • router_mapping: {}
  • learning_rate_mapping: {}

Training Logs

Epoch Step Training Loss Validation Loss
0.3906 100 4.8407 2.1680
0.7812 200 3.2924 1.7895
1.1719 300 2.7619 1.6139
1.5625 400 2.4898 1.5162
1.9531 500 2.3912 1.4297
2.3438 600 2.0123 1.3458
2.7344 700 1.9851 1.3046
3.125 800 1.8550 1.2478
3.5156 900 1.7236 1.2185
3.9062 1000 1.7033 1.1993
4.2969 1100 1.5782 1.1799
4.6875 1200 1.5676 1.1659

Training Time

  • Training: 13.5 minutes

Framework Versions

  • Python: 3.12.13
  • Sentence Transformers: 5.4.1
  • Transformers: 5.0.0
  • PyTorch: 2.10.0+cu128
  • Accelerate: 1.13.0
  • Datasets: 4.0.0
  • Tokenizers: 0.22.2

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{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}