Trelis/ms-marco-MiniLM-L-6-v2-2-cst-ep-MNRLtriplets-2e-5-batch32-gpu-overlap

SentenceTransformer based on cross-encoder/ms-marco-MiniLM-L-6-v2

This is a sentence-transformers model finetuned from cross-encoder/ms-marco-MiniLM-L-6-v2. It maps sentences & paragraphs to a 384-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: cross-encoder/ms-marco-MiniLM-L-6-v2 <!-- at revision b2cfda50a1a9fc7919e7444afbb52610d268af92 -->
• —Maximum Sequence Length: 512 tokens
• —Output Dimensionality: 384 tokens
• —Similarity Function: Cosine Similarity <!-- - Training Dataset: Unknown --> <!-- - 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': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, '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})
)

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("Trelis/ms-marco-MiniLM-L-6-v2-2-cst-ep-MNRLtriplets-2e-5-batch32-gpu-overlap")
# Run inference
sentences = [
    'What is the minimum number of digits allowed for identifying numbers according to clause 4.3.1?',
    '2. 2 teams playing unregistered players are liable to forfeit any match in which unregistered players have competed. fit playing rules - 5th edition copyright © touch football australia 2020 5 3 the ball 3. 1 the game is played with an oval, inflated ball of a shape, colour and size approved by fit or the nta. 3. 2 the ball shall be inflated to the manufacturers ’ recommended air pressure. 3. 3 the referee shall immediately pause the match if the size and shape of the ball no longer complies with clauses 3. 1 or 3. 2 to allow for the ball to replaced or the issue rectified. 3. 4 the ball must not be hidden under player attire. 4 playing uniform 4. 1 participating players are to be correctly attired in matching team uniforms 4. 2 playing uniforms consist of shirt, singlet or other item as approved by the nta or nta competition provider, shorts and / or tights and socks. 4. 3 all players are to wear a unique identifying number not less than 16cm in height, clearly displayed on the rear of the playing top. 4. 3. 1 identifying numbers must feature no more than two ( 2 ) digits.',
    '24. 5 for the avoidance of doubt for clauses 24. 3 and 24. 4 the non - offending team will retain a numerical advantage on the field of play during the drop - off. 25 match officials 25. 1 the referee is the sole judge on all match related matters inside the perimeter for the duration of a match, has jurisdiction over all players, coaches and officials and is required to : 25. 1. 1 inspect the field of play, line markings and markers prior to the commencement of the match to ensure the safety of all participants. 25. 1. 2 adjudicate on the rules of the game ; 25. 1. 3 impose any sanction necessary to control the match ; 25. 1. 4 award tries and record the progressive score ; 25. 1. 5 maintain a count of touches during each possession ; 25. 1. 6 award penalties for infringements against the rules ; and 25. 1. 7 report to the relevant competition administration any sin bins, dismissals or injuries to any participant sustained during a match. 25. 2 only team captains are permitted to seek clarification of a decision directly from the referee. an approach may only be made during a break in play or at the discretion of the referee.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

<!--

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. -->

<!--

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 Hyperparameters

Non-Default Hyperparameters

• —eval_strategy: steps
• —per_device_train_batch_size: 32
• —per_device_eval_batch_size: 32
• —learning_rate: 2e-05
• —num_train_epochs: 2
• —lr_scheduler_type: constant
• —warmup_ratio: 0.3
• —bf16: 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: 32
• —per_device_eval_batch_size: 32
• —per_gpu_train_batch_size: None
• —per_gpu_eval_batch_size: None
• —gradient_accumulation_steps: 1
• —eval_accumulation_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: 2
• —max_steps: -1
• —lr_scheduler_type: constant
• —lr_scheduler_kwargs: {}
• —warmup_ratio: 0.3
• —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: 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: {'minnumparams': 0, 'xla': False, 'xlafsdpv2': False, 'xlafsdpgrad_ckpt': False}
• —fsdp_transformer_layer_cls_to_wrap: None
• —accelerator_config: {'splitbatches': False, 'dispatchbatches': None, 'evenbatches': True, 'useseedablesampler': True, 'nonblocking': False, 'gradientaccumulationkwargs': 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: False
• —hub_always_push: False
• —gradient_checkpointing: False
• —gradient_checkpointing_kwargs: None
• —include_inputs_for_metrics: False
• —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
• —batch_sampler: batch_sampler
• —multi_dataset_batch_sampler: proportional

</details>

Training Logs

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

</details>

Framework Versions

• —Python: 3.10.12
• —Sentence Transformers: 3.0.1
• —Transformers: 4.42.3
• —PyTorch: 2.1.1+cu121
• —Accelerate: 0.31.0
• —Datasets: 2.17.1
• —Tokenizers: 0.19.1

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. -->