Hugging Face's logo

DChak2000
/
qwen3-trace-align

Sentence Similarity
sentence-transformers
Safetensors
feature-extraction
dense
Generated from Trainer
dataset_size:3156
loss:CosineSimilarityLoss
Model card Files
xet
Community
qwen3-trace-align / README.md
DChak2000's picture
DChak2000
LoRA fine-tuned for Prolog–NL trace alignment
2c519ed verified
preview code
|
raw
history blame contribute delete
11.6 kB
metadata 
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:3156
  - loss:CosineSimilarityLoss
base_model: Qwen/Qwen3-Embedding-8B
widget:
  - source_sentence: >-
      The goal nonvar('2019-12-31') succeeded, indicating that the date
      2019‑12‑31 is instantiated.
    sentences:
      - 'Succeeded: day_to_stamp("2019-12-31",1577836800.0)'
      - 'Failed: s1_c_iii(22895,3538)'
      - 'Failed: agent_(alice_dies,bob)'
  - source_sentence: The date September 1, 2015 corresponds to the Unix timestamp 1441152000.0.
    sentences:
      - 'Failed: son_(_20022)'
      - 'Succeeded: day_to_stamp("2015-09-01",1441152000.0)'
      - 'Failed: s1_c_iv(102268,27225)'
  - source_sentence: Alice is the employer of Bob.
    sentences:
      - 'Succeeded: agent_(alice_employer,bob)'
      - 'Succeeded: day_to_stamp("2019-10-10",1570752000.0)'
      - 'Failed: s7703_a(alice,_18952,_18954,2016)'
  - source_sentence: The first day of tax year 2014 is January 1, 2014.
    sentences:
      - 'Succeeded: nonvar("2019-10-10")'
      - 'Succeeded: first_day_year(2018,"2018-01-01")'
      - 'Succeeded: first_day_year(2014,"2014-01-01")'
  - source_sentence: Under section 1(a)(iv), the tax on $164,612 of taxable income is $44,789.
    sentences:
      - 'Succeeded: 2019 is 2018+1'
      - 'Succeeded: var(_21490)'
      - 'Succeeded: 44789 is round(35928.5+(164612-140000)*0.36)'
pipeline_tag: sentence-similarity
library_name: sentence-transformers

SentenceTransformer based on Qwen/Qwen3-Embedding-8B

This is a sentence-transformers model finetuned from Qwen/Qwen3-Embedding-8B. It maps sentences & paragraphs to a 4096-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-8B
  • Maximum Sequence Length: 40960 tokens
  • Output Dimensionality: 4096 dimensions
  • Similarity Function: Cosine Similarity

Model Sources

Full Model Architecture 

SentenceTransformer(
  (0): Transformer({'max_seq_length': 40960, 'do_lower_case': False, 'architecture': 'Qwen3Model'})
  (1): Pooling({'word_embedding_dimension': 4096, '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("DChak2000/qwen3-trace-align")
# Run inference
queries = [
    "Under section 1(a)(iv), the tax on $164,612 of taxable income is $44,789.",
]
documents = [
    'Succeeded: 44789 is round(35928.5+(164612-140000)*0.36)',
    'Succeeded: 2019 is 2018+1',
    'Succeeded: var(_21490)',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 4096] [3, 4096]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.0548, 0.3047, 0.3684]])

Training Details

Training Dataset

Unnamed Dataset

  • Size: 3,156 training samples
  • Columns: sentence_0, sentence_1, and label
  • Approximate statistics based on the first 1000 samples:
    sentence_0 sentence_1 label
    type string string float
    details
    • min: 5 tokens
    • mean: 23.92 tokens
    • max: 72 tokens
    • min: 6 tokens
    • mean: 23.48 tokens
    • max: 241 tokens
    • min: 0.0
    • mean: 0.83
    • max: 1.0
  • Samples:
    sentence_0 sentence_1 label
    The marriage predicate could not be satisfied. Failed: marriage_(_19298) 1.0
    The last day of the year 2018 is 2018-12-31. Succeeded: last_day_year(2018,"2018-12-31") 1.0
    The conversion of the date 2019‑11‑03 to a timestamp yielded 1572825600.0. Succeeded: day_to_stamp("2019-11-03",1572825600.0) 1.0
  • Loss: CosineSimilarityLoss with these parameters:
    {
    "loss_fct": "torch.nn.modules.loss.MSELoss"
}

Training Hyperparameters

Non-Default Hyperparameters

  • multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand
  • do_predict: False
  • eval_strategy: no
  • prediction_loss_only: True
  • per_device_train_batch_size: 8
  • per_device_eval_batch_size: 8
  • 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
  • num_train_epochs: 3
  • max_steps: -1
  • lr_scheduler_type: linear
  • lr_scheduler_kwargs: None
  • warmup_ratio: None
  • warmup_steps: 0
  • 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: False
  • 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
  • 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: batch_sampler
  • multi_dataset_batch_sampler: round_robin
  • router_mapping: {}
  • learning_rate_mapping: {}

Training Logs

Epoch Step Training Loss
1.2658 500 0.0683
2.5316 1000 0.0309

Framework Versions

  • Python: 3.10.19
  • Sentence Transformers: 5.2.2
  • Transformers: 5.0.0
  • PyTorch: 2.5.1+cu121
  • 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",
}