tani-at-nola/paws-MiniLM-v0.1

CrossEncoder

This is a Cross Encoder model trained on the paws dataset using the sentence-transformers library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.

Model Details

Model Description

• Model Type: Cross Encoder
• Maximum Sequence Length: 512 tokens
• Number of Output Labels: 1 label
• Training Dataset:
  • paws
• Language: en

Model Sources

• Documentation: Sentence Transformers Documentation
• Documentation: Cross Encoder Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Cross Encoders on Hugging Face

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 CrossEncoder

# Download from the 🤗 Hub
model = CrossEncoder("tani-at-nola/paws-MiniLM-v0.1")
# Get scores for pairs of texts
pairs = [
    ['This was a series of nested angular standards , so that measurements in azimuth and elevation could be done directly in polar coordinates relative to the ecliptic .', 'This was a series of nested polar scales , so that measurements in azimuth and elevation could be performed directly in angular coordinates relative to the ecliptic .'],
    ['His father emigrated to Missouri in 1868 but returned when his wife became ill and before the rest of the family could also go to America .', 'His father emigrated to America in 1868 , but returned when his wife became ill and before the rest of the family could go to Missouri .'],
    ['In January 2011 , the Deputy Secretary General of FIBA Asia , Hagop Khajirian , inspected the venue together with SBP - President Manuel V. Pangilinan .', 'In January 2011 , FIBA Asia deputy secretary general Hagop Khajirian along with SBP president Manuel V. Pangilinan inspected the venue .'],
    ['Steiner argued that , in the right circumstances , the spiritual world can be explored through direct experience by practicing ethical and cognitive forms of rigorous self-discipline .', 'Steiner held that the spiritual world can be researched in the right circumstances through direct experience , by persons practicing rigorous forms of ethical and cognitive self-discipline .'],
    ['Luciano Williames Dias ( born July 25 , 1970 ) is a Brazilian football coach and former player .', 'Luciano Williames Dias ( born 25 July 1970 ) is a former football coach and Brazilian player .'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'This was a series of nested angular standards , so that measurements in azimuth and elevation could be done directly in polar coordinates relative to the ecliptic .',
    [
        'This was a series of nested polar scales , so that measurements in azimuth and elevation could be performed directly in angular coordinates relative to the ecliptic .',
        'His father emigrated to America in 1868 , but returned when his wife became ill and before the rest of the family could go to Missouri .',
        'In January 2011 , FIBA Asia deputy secretary general Hagop Khajirian along with SBP president Manuel V. Pangilinan inspected the venue .',
        'Steiner held that the spiritual world can be researched in the right circumstances through direct experience , by persons practicing rigorous forms of ethical and cognitive self-discipline .',
        'Luciano Williames Dias ( born 25 July 1970 ) is a former football coach and Brazilian player .',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Training Details

Training Dataset

paws

• Dataset: paws at 161ece9
• Size: 49,401 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 29 characters mean: 112.38 characters max: 202 characters	min: 24 characters mean: 112.65 characters max: 207 characters	0: ~55.60% 1: ~44.40%

• Samples:

  sentence1	sentence2	label
  In Paris , in October 1560 , he secretly met the English ambassador , Nicolas Throckmorton , asking him for a passport to return to England through Scotland .	In October 1560 , he secretly met with the English ambassador , Nicolas Throckmorton , in Paris , and asked him for a passport to return to Scotland through England .	0
  The NBA season of 1975 -- 76 was the 30th season of the National Basketball Association .	The 1975 -- 76 season of the National Basketball Association was the 30th season of the NBA .	1
  There are also specific discussions , public profile debates and project discussions .	There are also public discussions , profile specific discussions , and project discussions .	0

• Loss: BinaryCrossEntropyLoss with these parameters:

  {
      "activation_fn": "torch.nn.modules.linear.Identity",
      "pos_weight": null
  }
  

Evaluation Dataset

paws

• Dataset: paws at 161ece9
• Size: 8,000 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 36 characters mean: 115.22 characters max: 193 characters	min: 35 characters mean: 115.21 characters max: 193 characters	0: ~56.10% 1: ~43.90%

• Samples:

  sentence1	sentence2	label
  This was a series of nested angular standards , so that measurements in azimuth and elevation could be done directly in polar coordinates relative to the ecliptic .	This was a series of nested polar scales , so that measurements in azimuth and elevation could be performed directly in angular coordinates relative to the ecliptic .	0
  His father emigrated to Missouri in 1868 but returned when his wife became ill and before the rest of the family could also go to America .	His father emigrated to America in 1868 , but returned when his wife became ill and before the rest of the family could go to Missouri .	0
  In January 2011 , the Deputy Secretary General of FIBA Asia , Hagop Khajirian , inspected the venue together with SBP - President Manuel V. Pangilinan .	In January 2011 , FIBA Asia deputy secretary general Hagop Khajirian along with SBP president Manuel V. Pangilinan inspected the venue .	1

• Loss: BinaryCrossEntropyLoss with these parameters:

  {
      "activation_fn": "torch.nn.modules.linear.Identity",
      "pos_weight": null
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• fp16: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 8
• per_device_eval_batch_size: 8
• 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: 2e-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: 0.1
• 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: 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: 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}
• 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
• dispatch_batches: None
• split_batches: 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
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss
0.0810	500	0.5927
0.1619	1000	0.5627
0.2429	1500	0.5573
0.3238	2000	0.53
0.4048	2500	0.5049
0.4858	3000	0.4804
0.5667	3500	0.4976
0.6477	4000	0.4803

Framework Versions

• Python: 3.13.5
• Sentence Transformers: 5.0.0
• Transformers: 4.49.0
• PyTorch: 2.6.0
• Accelerate: 1.8.1
• Datasets: 3.3.2
• Tokenizers: 0.21.0

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",
}