checkpoint-16568/README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:529974
  - loss:MultipleNegativesSymmetricRankingLoss
base_model: sentence-transformers/all-MiniLM-L6-v2
widget:
  - source_sentence: essence multi task concealer 15 natural nude
    sentences:
      - ahc vitamin c sheet mask
      - ' concealer'
      - face make-up
  - source_sentence: casa chandelier
    sentences:
      - hand braided chandelier
      - chandlier
      - disney princess belle styling head playset, brown hair
  - source_sentence: fender squier classic vibe '50s stratocaster, maple fingerboard
    sentences:
      - guitar
      - right handed guitar
      - endowments of the two holy sanctuaries
  - source_sentence: faber castell jumbo colored pencil, metallic copper
    sentences:
      - pencil
      - ' faber castell colored pencil'
      - the essential notebook-green
  - source_sentence: farm frites potato chips
    sentences:
      - juhayna - long life tangerine mandarin fruit drink - 1 l
      - farm frites chips
      - snacks
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy
model-index:
  - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
    results:
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy
            value: 0.9684509634971619
            name: Cosine Accuracy

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

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

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("LamaDiab/MiniLM-V21Data-256ConstantBATCH-SemanticEngine")
# Run inference
sentences = [
    'farm frites potato chips',
    'farm frites chips',
    'juhayna - long life tangerine mandarin fruit drink - 1 l',
]
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, 0.9623, 0.1274],
#         [0.9623, 1.0000, 0.0953],
#         [0.1274, 0.0953, 1.0000]])

Evaluation

Metrics

Triplet

• Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.9685

Training Details

Training Dataset

Unnamed Dataset

• Size: 529,974 training samples
• Columns: anchor, positive, and itemCategory
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	itemCategory
  type	string	string	string
  details	min: 3 tokens mean: 10.64 tokens max: 44 tokens	min: 3 tokens mean: 4.83 tokens max: 105 tokens	min: 3 tokens mean: 3.88 tokens max: 9 tokens

• Samples:

  anchor	positive	itemCategory
  girls’ ski base layer top bl 100 black	high neck top	top
  lamar tom barista coffee milk no added sugar	naturally sweetened almond milk	dairy
  powder drink	beverage	beverage

• Loss: MultipleNegativesSymmetricRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false
  }
  

Evaluation Dataset

Unnamed Dataset

• Size: 9,509 evaluation samples
• Columns: anchor, positive, negative, and itemCategory
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative	itemCategory
  type	string	string	string	string
  details	min: 3 tokens mean: 9.63 tokens max: 43 tokens	min: 2 tokens mean: 6.34 tokens max: 150 tokens	min: 3 tokens mean: 9.35 tokens max: 60 tokens	min: 3 tokens mean: 3.88 tokens max: 10 tokens

• Samples:

  anchor	positive	negative	itemCategory
  pilot mechanical pencil progrex h-127 - 0.7 mm	mechanical pencil	colorful sky bitch medal	pencil
  superior drawing marker -pen - set of 12 colors - 2 nib	nib marker pen	plastic holder with capsule	marker
  first person singular author: haruki murakami	first person singular	metal single rods - rustic cage rod	literature and fiction

• Loss: MultipleNegativesSymmetricRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 256
• per_device_eval_batch_size: 256
• learning_rate: 2e-05
• weight_decay: 0.001
• num_train_epochs: 8
• warmup_ratio: 0.2
• fp16: True
• dataloader_num_workers: 1
• dataloader_prefetch_factor: 2
• dataloader_persistent_workers: True
• push_to_hub: True
• hub_model_id: LamaDiab/MiniLM-V21Data-256ConstantBATCH-SemanticEngine
• hub_strategy: all_checkpoints

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 256
• per_device_eval_batch_size: 256
• 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: 0.001
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 8
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.2
• 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: 1
• dataloader_prefetch_factor: 2
• 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: True
• skip_memory_metrics: True
• use_legacy_prediction_loop: False
• push_to_hub: True
• resume_from_checkpoint: None
• hub_model_id: LamaDiab/MiniLM-V21Data-256ConstantBATCH-SemanticEngine
• hub_strategy: all_checkpoints
• 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: False
• 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: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	cosine_accuracy
0.0005	1	4.1585	-	-
0.4829	1000	3.2055	0.5676	0.9401
0.9657	2000	2.0069	0.5089	0.9479
1.4481	3000	1.8871	0.4805	0.9564
1.9305	4000	1.6352	0.4756	0.9602
2.4129	5000	1.4252	0.4694	0.9619
2.8953	6000	1.2913	0.4598	0.9642
3.3777	7000	1.1875	0.4547	0.9643
3.8601	8000	1.1294	0.4529	0.9651
4.3425	9000	1.054	0.4549	0.9661
4.8249	10000	1.0193	0.4545	0.9672
5.3073	11000	0.9886	0.4524	0.9666
5.7897	12000	0.9365	0.4461	0.9676
6.2721	13000	0.929	0.4498	0.9687
6.7545	14000	0.91	0.4490	0.9678
7.2369	15000	0.8904	0.4486	0.9683
7.7192	16000	0.8718	0.4479	0.9685

Framework Versions

• Python: 3.11.13
• Sentence Transformers: 5.1.2
• Transformers: 4.53.3
• PyTorch: 2.6.0+cu124
• Accelerate: 1.9.0
• Datasets: 4.4.1
• Tokenizers: 0.21.2

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",
}