embeddinggemma-300m-finetune-news-finalize

SentenceTransformer based on google/embeddinggemma-300m

This is a sentence-transformers model finetuned from google/embeddinggemma-300m on the train 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: google/embeddinggemma-300m <!-- at revision 57c266a740f537b4dc058e1b0cda161fd15afa75 -->
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • train

<!-- - **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': 256, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'})
  (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): Dense({'in_features': 768, 'out_features': 3072, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
  (3): Dense({'in_features': 3072, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
  (4): 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("b00l26/embeddinggemma-300m-finetune-news-finalize")
# Run inference
queries = [
    "M\u1ef9 \u0111i\u1ec1u_tra tu\u00e2n_th\u1ee7 tho\u1ea3_thu\u1eadn th\u01b0\u01a1ng_m\u1ea1i Trung_Qu\u1ed1c . V\u0103n_ph\u00f2ng \u0110\u1ea1i_di\u1ec7n Th\u01b0\u01a1ng_m\u1ea1i M\u1ef9 ( USTR ) \u0111i\u1ec1u_tra tu\u00e2n_th\u1ee7 tho\u1ea3_thu\u1eadn th\u01b0\u01a1ng_m\u1ea1i Trung_Qu\u1ed1c k\u00fd_k\u1ebft 2020 .",
]
documents = [
    "Trung_Quốc đồng_ý đàm_phán thương_mại ' ' Mỹ . Trung_Quốc đồng_ý tiến_hành vòng đàm_phán thương_mại Mỹ   .",
    'Thời_điểm đẹp Hà_Giang ngắm tam_giác mạch ? . Du_khách Hà_Nội ngắm hoa tam_giác mạch Hà_Giang , tư_vấn hoa nở_rộ , rực_rỡ .',
    'Bất_động_sản Nam trở_lại đường_đua sáp_nhập địa_giới hành_chính . ( Dân_trí ) - Trong cung lõi TPHCM khan_hiếm khu_vực lân_cận Bình_Dương , Long_An Đồng_Nai ( cũ ) dồi_dào , đa_dạng phân khúc .',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 768] [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.6707,  0.0895, -0.0779]])

<!-- ### 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

Information Retrieval

• Evaluated with <code>InformationRetrievalEvaluator</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

train

• Dataset: train
• Size: 26,696 training samples
• Columns: <code>anchor</code> and <code>positive</code>
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	<ul><li>min: 23 tokens</li><li>mean: 72.82 tokens</li><li>max: 141 tokens</li></ul>	<ul><li>min: 27 tokens</li><li>mean: 73.87 tokens</li><li>max: 132 tokens</li></ul>

• Samples:

  anchor	positive
  <code>Nam_Định : Thuê thần đèn di_dời 500 đường điện . ( Dân_trí ) - Tiếc 2 tầng xây_dựng khả_năng dỡ , Thuế mua chi nửa tỷ đồng thuê thần đèn di_chuyển đất .</code>	<code>Mục_sở_thị mỏng Vương_quốc_Anh rao 1,3 triệu USD . Ngôi nằm ga tàu_điện_ngầm Goldhawk_Road tây London , rộng 6 mét , 5 tầng tổng diện_tích 1.034 mét_vuông . Tuy mỏng , rao giá 950.000 bảng Anh ( 1,3 triệu USD ) .</code>
  <code>Trang_trí đám_cưới , đám_hỏi kiêng sen trắng cành trúc ? . Theo chuyên_gia văn_hoá , không_gian chùa_chiền , đám hiếu ngược đám_cưới đám_cưới . Tuy_nhiên , , quan_niệm dần .</code>	<code>Đại_gia TPHCM chi tiền tỷ tổ_chức đám_cưới bảo_mẫu . ( Dân_trí ) - Vì đem nữ bảo_mẫu gia_đình đám_cưới , nữ đại_gia TPHCM chi tiền tổ_chức tiệc cưới bảo_mẫu .</code>
  <code>Đệ phu_nhân Pháp chỉ_trích miệt_thị biểu_tình . Những nổi_tiếng chính_trị_gia cánh tả Pháp bày_tỏ phẫn_nộ Brigitte_Macron cụm_từ lũ đàn_bà ngu_ngốc hoạt_động nữ_quyền .</code>	<code>Đệ phu_nhân Pháp ám_ảnh đồn giới_tính . Auziere , gái của Đệ nhất phu_nhân Pháp , nói rằng mẹ lo_âu sâu_sắc xoay quanh ̃ng đồn thất thiệt về giới tính .</code>

• Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 512
• per_device_eval_batch_size: 64
• gradient_accumulation_steps: 4
• num_train_epochs: 40
• warmup_ratio: 0.1
• bf16: True
• dataloader_num_workers: 2
• dataloader_pin_memory: False
• gradient_checkpointing: 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: 512
• per_device_eval_batch_size: 64
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 4
• 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: 40
• 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: True
• 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: 2
• 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}
• tp_size: 0
• 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: False
• 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: True
• 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

Framework Versions

• Python: 3.10.19
• Sentence Transformers: 5.2.0
• Transformers: 4.51.0
• PyTorch: 2.1.2+cu118
• Accelerate: 0.34.2
• Datasets: 3.3.2
• Tokenizers: 0.21.4

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.* -->