Qwen3-Embedding-0.6B-netsecgame-finetuned-pairs2

SentenceTransformer based on Qwen/Qwen3-Embedding-0.6B

This is a sentence-transformers model finetuned from Qwen/Qwen3-Embedding-0.6B on the netsecgame-embedding-finetuning-pairs-topology 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: Qwen/Qwen3-Embedding-0.6B <!-- at revision c54f2e6e80b2d7b7de06f51cec4959f6b3e03418 -->
• Maximum Sequence Length: 32768 tokens
• Output Dimensionality: 1024 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • netsecgame-embedding-finetuning-pairs-topology

<!-- - **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': 32768, 'do_lower_case': False, 'architecture': 'Qwen3Model'})
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': True, '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("stratosphere/Qwen3-Embedding-0.6B-netsecgame-finetuned-pairs2")
# Run inference
queries = [
    "[NETS] 192.168.3.0/24, 192.168.2.0/24, 213.47.23.192/26, 192.168.1.0/24 [HOSTS] 192.168.2.3, 192.168.2.6, 192.168.2.2, 192.168.2.5, 192.168.2.4, 213.47.23.195, 192.168.1.4, 192.168.1.2, 192.168.2.1, 192.168.1.3 [CTRL] 213.47.23.195, 192.168.2.2 [SRVC] 192.168.2.2, 213.47.23.195, 192.168.2.4, 192.168.1.2",
]
documents = [
    '[NETS] 192.168.3.0/24, 192.168.2.0/24, 213.47.23.192/26, 192.168.1.0/24 [HOSTS] 192.168.2.3, 192.168.2.6, 192.168.2.2, 192.168.2.5, 192.168.2.4, 213.47.23.195, 192.168.1.4, 192.168.1.2, 192.168.2.1, 192.168.1.3 [CTRL] 213.47.23.195, 192.168.2.2 [SRVC] 192.168.2.2, 213.47.23.195, 192.168.2.5, 192.168.1.2',
    '[NETS] 10.0.46.0/24, 10.0.47.0/24, 10.0.45.0/24, 55.34.2.4/26 [HOSTS] 10.0.46.6, 10.0.47.1, 10.0.47.6, 10.0.46.1, 10.0.47.3, 10.0.47.4, 55.34.2.5, 10.0.47.5, 10.0.47.2, 10.0.46.2, 10.0.46.4, 10.0.46.3, 10.0.46.5 [CTRL] 10.0.47.3, 10.0.47.4, 55.34.2.5, 10.0.47.2, 10.0.46.3 [SRVC] 55.34.2.5, 10.0.46.2, 10.0.47.2, 10.0.47.4, 10.0.46.3, 10.0.47.3, 10.0.46.5, 10.0.46.4, 10.0.47.5 [DATA] 10.0.47.4, 10.0.47.2, 10.0.47.3',
    '[NETS] 172.19.0.0/24, 54.123.53.29/26, 172.19.1.0/24, 172.19.2.0/24 [HOSTS] 172.19.1.4, 172.19.1.1, 101.32.5.23, 172.19.1.5, 172.19.2.2, 172.19.2.3, 172.19.1.6, 172.19.1.3, 172.19.2.4, 172.19.1.2 [CTRL] 172.19.1.4, 172.19.1.5, 101.32.5.23, 172.19.2.3, 172.19.1.3, 172.19.2.4 [SRVC] 101.32.5.23, 172.19.1.5, 172.19.1.3, 172.19.2.4, 172.19.2.3, 172.19.1.4, 172.19.2.2',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 1024] [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.0644, 0.0168, 0.0084]])

<!-- ### 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

Binary Classification

• Dataset: topology_val
• Evaluated with <code>BinaryClassificationEvaluator</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

netsecgame-embedding-finetuning-pairs-topology

• Dataset: netsecgame-embedding-finetuning-pairs-topology at 8c78c97
• Size: 21,011 training samples
• Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	<ul><li>min: 121 tokens</li><li>mean: 289.98 tokens</li><li>max: 463 tokens</li></ul>	<ul><li>min: 121 tokens</li><li>mean: 291.36 tokens</li><li>max: 504 tokens</li></ul>	<ul><li>min: 0.0</li><li>mean: 0.5</li><li>max: 1.0</li></ul>

• Samples:

  sentence1	sentence2	label
  <code>[NETS] 172.20.7.0/24, 172.20.6.0/24, 172.20.8.0/24, 32.8.23.1/26 [HOSTS] 172.20.8.2, 172.20.7.1, 172.20.8.4, 172.20.7.6, 172.20.7.4, 172.20.7.5, 172.20.7.3, 172.20.8.3, 32.8.23.1, 172.20.7.2 [CTRL] 32.8.23.1, 172.20.7.2 [SRVC] 32.8.23.1, 172.20.7.3, 172.20.7.5</code>	<code>[NETS] 172.20.7.0/24, 172.20.6.0/24, 172.20.8.0/24, 32.8.23.1/26 [HOSTS] 172.20.8.2, 172.20.7.1, 172.20.8.4, 172.20.7.6, 172.20.7.4, 172.20.7.5, 172.20.7.3, 172.20.8.3, 32.8.23.1, 172.20.7.2 [CTRL] 172.20.7.5, 32.8.23.1 [SRVC] 32.8.23.1, 172.20.7.3, 172.20.7.4</code>	<code>1.0</code>
  <code>[NETS] 192.168.3.0/24, 192.168.2.0/24, 213.47.23.192/26, 192.168.1.0/24 [HOSTS] 192.168.2.3, 192.168.2.6, 192.168.2.2, 192.168.2.5, 192.168.2.4, 213.47.23.195, 192.168.1.4, 192.168.1.2, 192.168.2.1, 192.168.1.3 [CTRL] 192.168.2.4, 213.47.23.195, 192.168.2.2, 192.168.2.3 [SRVC] 213.47.23.195, 192.168.2.5, 192.168.2.3, 192.168.2.4, 192.168.2.2</code>	<code>[NETS] 10.7.44.0/24, 10.7.45.0/24, 54.123.53.29/26, 10.7.43.0/24 [HOSTS] 10.7.44.6, 10.7.45.4, 10.7.44.4, 10.7.44.5, 10.7.44.1, 10.7.44.3, 10.7.45.2, 10.7.45.3, 54.123.53.21, 10.7.44.2 [CTRL] 10.7.45.4, 54.123.53.21, 10.7.44.6 [SRVC] 54.123.53.21, 10.7.45.4, 10.7.44.5, 10.7.44.3</code>	<code>0.0</code>
  <code>[NETS] 172.20.7.0/24, 172.20.6.0/24, 172.20.8.0/24, 32.8.23.1/26 [HOSTS] 172.20.8.2, 172.20.7.1, 172.20.8.4, 172.20.7.6, 172.20.7.4, 172.20.7.5, 172.20.7.3, 172.20.8.3, 32.8.23.1, 172.20.7.2 [CTRL] 32.8.23.1, 172.20.7.2 [SRVC] 172.20.7.2, 172.20.7.3, 32.8.23.1</code>	<code>[NETS] 172.20.7.0/24, 172.20.6.0/24, 172.20.8.0/24, 32.8.23.1/26 [HOSTS] 172.20.8.2, 172.20.7.1, 172.20.8.4, 172.20.7.6, 172.20.7.4, 172.20.7.5, 172.20.7.3, 172.20.8.3, 32.8.23.1, 172.20.7.2 [CTRL] 32.8.23.1, 172.20.7.3 [SRVC] 172.20.7.3, 172.20.7.2, 32.8.23.1</code>	<code>1.0</code>

• Loss: <code>OnlineContrastiveLoss</code>

Evaluation Dataset

netsecgame-embedding-finetuning-pairs-topology

• Dataset: netsecgame-embedding-finetuning-pairs-topology at 8c78c97
• Size: 2,626 evaluation samples
• Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	<ul><li>min: 140 tokens</li><li>mean: 290.95 tokens</li><li>max: 461 tokens</li></ul>	<ul><li>min: 140 tokens</li><li>mean: 292.04 tokens</li><li>max: 448 tokens</li></ul>	<ul><li>min: 0.0</li><li>mean: 0.51</li><li>max: 1.0</li></ul>

• Samples:

  sentence1	sentence2	label
  <code>[NETS] 192.168.3.0/24, 192.168.2.0/24, 213.47.23.192/26, 192.168.1.0/24 [HOSTS] 192.168.2.3, 192.168.2.6, 192.168.2.2, 192.168.2.5, 192.168.2.4, 213.47.23.195, 192.168.1.4, 192.168.1.2, 192.168.2.1, 192.168.1.3 [CTRL] 192.168.2.2, 213.47.23.195, 192.168.2.3 [SRVC] 192.168.2.2, 213.47.23.195, 192.168.2.5, 192.168.2.4, 192.168.2.3</code>	<code>[NETS] 192.168.3.0/24, 192.168.2.0/24, 213.47.23.192/26, 192.168.1.0/24 [HOSTS] 192.168.2.3, 192.168.2.6, 192.168.2.2, 192.168.2.5, 192.168.2.4, 213.47.23.195, 192.168.1.4, 192.168.1.2, 192.168.2.1, 192.168.1.3 [CTRL] 192.168.2.4, 213.47.23.195, 192.168.2.3 [SRVC] 192.168.2.3, 213.47.23.195, 192.168.2.4, 192.168.2.5, 192.168.2.2</code>	<code>1.0</code>
  <code>[NETS] 10.7.44.0/24, 10.7.45.0/24, 54.123.53.29/26, 10.7.43.0/24 [HOSTS] 10.7.44.6, 10.7.45.4, 10.7.44.4, 10.7.44.5, 10.7.44.1, 10.7.44.3, 10.7.45.2, 10.7.45.3, 54.123.53.21, 10.7.44.2 [CTRL] 54.123.53.21, 10.7.45.4, 10.7.44.4, 10.7.44.2 [SRVC] 54.123.53.21, 10.7.44.4, 10.7.44.2, 10.7.45.4</code>	<code>[NETS] 172.20.7.0/24, 172.20.6.0/24, 172.20.8.0/24, 32.8.23.1/26 [HOSTS] 172.20.8.2, 172.20.7.1, 172.20.8.4, 172.20.7.6, 172.20.7.4, 172.20.7.5, 172.20.7.3, 172.20.8.3, 32.8.23.1, 172.20.7.2 [CTRL] 172.20.7.4, 32.8.23.1, 172.20.7.3, 172.20.7.2 [SRVC] 32.8.23.1, 172.20.7.2, 172.20.7.3, 172.20.7.4</code>	<code>0.0</code>
  <code>[NETS] 172.20.7.0/24, 172.20.6.0/24, 172.20.8.0/24, 32.8.23.1/26 [HOSTS] 172.20.8.2, 172.20.7.1, 172.20.8.4, 172.20.7.6, 172.20.7.4, 172.20.7.5, 172.20.7.3, 172.20.8.3, 32.8.23.1, 172.20.7.2 [CTRL] 172.20.7.4, 172.20.8.2, 32.8.23.1, 172.20.7.2 [SRVC] 172.20.7.2, 172.20.7.4, 172.20.7.3, 172.20.8.2, 32.8.23.1, 172.20.7.5, 172.20.8.4</code>	<code>[NETS] 172.19.0.0/24, 54.123.53.29/26, 172.19.1.0/24, 172.19.2.0/24 [HOSTS] 172.19.1.4, 172.19.1.1, 101.32.5.23, 172.19.1.5, 172.19.2.2, 172.19.2.3, 172.19.1.6, 172.19.1.3, 172.19.2.4, 172.19.1.2 [CTRL] 172.19.2.2, 172.19.2.4, 101.32.5.23, 172.19.1.2 [SRVC] 172.19.1.2, 101.32.5.23, 172.19.2.2, 172.19.1.4, 172.19.2.4</code>	<code>0.0</code>

• Loss: <code>OnlineContrastiveLoss</code>

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 2
• gradient_accumulation_steps: 4
• learning_rate: 1e-06
• weight_decay: 0.01
• num_train_epochs: 1
• fp16: True
• load_best_model_at_end: True

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: 2
• per_device_eval_batch_size: 8
• 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: 1e-06
• weight_decay: 0.01
• 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: None
• warmup_ratio: 0.0
• 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
• 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}
• parallelism_config: None
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch_fused
• optim_args: None
• adafactor: False
• 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
• 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
• hub_revision: None
• 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: 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
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

</details>

Training Logs

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

• The bold row denotes the saved checkpoint.

</details>

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 5.2.0
• Transformers: 4.57.6
• PyTorch: 2.10.0+cu128
• Accelerate: 1.12.0
• Datasets: 4.5.0
• 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",
}

<!-- ## 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.* -->