mehularora/scrabble-embed-v1

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the csv dataset. 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: sentence-transformers/all-MiniLM-L6-v2
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • csv

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': '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})
  (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("Mehularora/scrabble-embed-v1")
# Run inference
sentences = [
    'BOLDING',
    '< BOLD, confident and fearless [adj]',
    '< NAUCH, nautch (intricate traditional Indian dance) [n]',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.7391, 0.0112],
#         [0.7391, 1.0000, 0.0722],
#         [0.0112, 0.0722, 1.0000]])

Evaluation

Metrics

Information Retrieval

• Dataset: dictionary-test
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.597
cosine_accuracy@3	0.7253
cosine_accuracy@5	0.7496
cosine_accuracy@10	0.7743
cosine_precision@1	0.597
cosine_precision@3	0.2418
cosine_precision@5	0.1499
cosine_precision@10	0.0774
cosine_recall@1	0.597
cosine_recall@3	0.7253
cosine_recall@5	0.7496
cosine_recall@10	0.7743
cosine_ndcg@10	0.6919
cosine_mrr@10	0.6649
cosine_map@100	0.6677

Training Details

Training Dataset

csv

• Dataset: csv
• Size: 227,518 training samples
• Columns: word and definition
• Approximate statistics based on the first 1000 samples:

  	word	definition
  type	string	string
  details	min: 3 tokens mean: 4.9 tokens max: 9 tokens	min: 6 tokens mean: 15.82 tokens max: 44 tokens

• Samples:

  word	definition
  SLURPIEST	< SLURPY, making a slurping noise [adj]
  CRISPNESSES	< CRISPNESS, < CRISP, fresh and firm [adj]
  CECUTIENCY	a tendency to blindness [n]

• Loss: MatryoshkaLoss with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          384,
          256
      ],
      "matryoshka_weights": [
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 64
• learning_rate: 2e-05
• num_train_epochs: 1
• fp16: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 64
• 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: 0.0
• 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: 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}
• 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: {}

Training Logs

Epoch	Step	Training Loss	dictionary-test_cosine_ndcg@10
0.0281	100	1.5353	0.6306
0.0563	200	1.2836	0.6543
0.0844	300	1.2305	0.6637
0.1125	400	1.1669	0.6651
0.1406	500	1.1904	0.6714
0.1688	600	1.0998	0.6738
0.1969	700	1.0655	0.6751
0.2250	800	1.095	0.6781
0.2532	900	1.1535	0.6813
0.2813	1000	1.0047	0.6814
0.3094	1100	1.0749	0.6809
0.3376	1200	1.0642	0.6813
0.3657	1300	1.0718	0.6851
0.3938	1400	1.023	0.6854
0.4219	1500	1.0429	0.6850
0.4501	1600	1.0088	0.6849
0.4782	1700	1.0129	0.6873
0.5063	1800	0.988	0.6874
0.5345	1900	1.0413	0.6882
0.5626	2000	1.0043	0.6885
0.5907	2100	0.9929	0.6886
0.6188	2200	0.9403	0.6899
0.6470	2300	0.9789	0.6907
0.6751	2400	0.9595	0.6912
0.7032	2500	0.9786	0.6914
0.7314	2600	0.9647	0.6911
0.7595	2700	0.9245	0.6897
0.7876	2800	0.9685	0.6906
0.8158	2900	0.9778	0.6896
0.8439	3000	0.939	0.6906
0.8720	3100	0.9822	0.6904
0.9001	3200	1.0038	0.6913
0.9283	3300	0.9297	0.6910
0.9564	3400	0.9215	0.6915
0.9845	3500	0.948	0.6919

Framework Versions

• Python: 3.11.4
• Sentence Transformers: 5.1.2
• Transformers: 4.57.3
• PyTorch: 2.9.1+cpu
• Accelerate: 1.12.0
• Datasets: 4.4.1
• Tokenizers: 0.22.1

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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

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}
}