DannyAI/embedding_fine_tuning_matryoshka_loss_bge_large_en_v1.5

bge-large-en-v1.5

This is a sentence-transformers model finetuned from BAAI/bge-large-en-v1.5 on the all-nli dataset. It maps sentences & paragraphs to a 1024-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: BAAI/bge-large-en-v1.5
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 1024 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • all-nli
• Language: en
• License: mit

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': True, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, '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': 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
matryoshka_dims = [1024,768,512,256,128,64] # for truncating the dimensions
model = SentenceTransformer("DannyAI/embedding_fine_tuning_adaptive_layer_matryoshka2dloss_bge_large_en_v1.5",
truncate_dim=matryoshka_dims[0])
# Run inference
sentences = [
    'Young boy kicks a soccer ball towards the goal as the crowd watches.',
    'The boy is under the age of eighteen.',
    'The boy is alone in his backyard.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.6018, 0.3989],
#         [0.6018, 1.0000, 0.6269],
#         [0.3989, 0.6269, 1.0000]])

Evaluation

Metrics

Triplet

• Datasets: all-nli-val-1024 and all-nli-test-1024
• Evaluated with TripletEvaluator with these parameters:

  {
      "truncate_dim": 1024
  }
  

Metric	all-nli-val-1024	all-nli-test-1024
cosine_accuracy	0.9507	0.9532

Triplet

• Datasets: all-nli-val-768 and all-nli-test-768
• Evaluated with TripletEvaluator with these parameters:

  {
      "truncate_dim": 768
  }
  

Metric	all-nli-val-768	all-nli-test-768
cosine_accuracy	0.9497	0.9516

Triplet

• Datasets: all-nli-val-512 and all-nli-test-512
• Evaluated with TripletEvaluator with these parameters:

  {
      "truncate_dim": 512
  }
  

Metric	all-nli-val-512	all-nli-test-512
cosine_accuracy	0.9477	0.9504

Triplet

• Datasets: all-nli-val-256 and all-nli-test-256
• Evaluated with TripletEvaluator with these parameters:

  {
      "truncate_dim": 256
  }
  

Metric	all-nli-val-256	all-nli-test-256
cosine_accuracy	0.9453	0.9493

Triplet

• Datasets: all-nli-val-128 and all-nli-test-128
• Evaluated with TripletEvaluator with these parameters:

  {
      "truncate_dim": 128
  }
  

Metric	all-nli-val-128	all-nli-test-128
cosine_accuracy	0.9393	0.9452

Triplet

• Datasets: all-nli-val-64 and all-nli-test-64
• Evaluated with TripletEvaluator with these parameters:

  {
      "truncate_dim": 64
  }
  

Metric	all-nli-val-64	all-nli-test-64
cosine_accuracy	0.931	0.9363

Training Details

Training Dataset

all-nli

• Dataset: all-nli at d482672
• Size: 200,000 training samples
• Columns: anchor, positive, and negative
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative
  type	string	string	string
  details	min: 7 tokens mean: 10.46 tokens max: 46 tokens	min: 6 tokens mean: 12.81 tokens max: 40 tokens	min: 5 tokens mean: 13.4 tokens max: 50 tokens

• Samples:

  anchor	positive	negative
  A person on a horse jumps over a broken down airplane.	A person is outdoors, on a horse.	A person is at a diner, ordering an omelette.
  Children smiling and waving at camera	There are children present	The kids are frowning
  A boy is jumping on skateboard in the middle of a red bridge.	The boy does a skateboarding trick.	The boy skates down the sidewalk.

• Loss: MatryoshkaLoss with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          1024,
          768,
          512,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Evaluation Dataset

all-nli

• Dataset: all-nli at d482672
• Size: 3,000 evaluation samples
• Columns: anchor, positive, and negative
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative
  type	string	string	string
  details	min: 6 tokens mean: 17.95 tokens max: 63 tokens	min: 4 tokens mean: 9.78 tokens max: 29 tokens	min: 5 tokens mean: 10.35 tokens max: 29 tokens

• Samples:

  anchor	positive	negative
  Two women are embracing while holding to go packages.	Two woman are holding packages.	The men are fighting outside a deli.
  Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.	Two kids in numbered jerseys wash their hands.	Two kids in jackets walk to school.
  A man selling donuts to a customer during a world exhibition event held in the city of Angeles	A man selling donuts to a customer.	A woman drinks her coffee in a small cafe.

• Loss: MatryoshkaLoss with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          1024,
          768,
          512,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 5
• per_device_eval_batch_size: 5
• learning_rate: 2e-05
• max_steps: 100
• warmup_ratio: 0.1
• seed: 30
• bf16: True
• load_best_model_at_end: True
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 5
• per_device_eval_batch_size: 5
• 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: 3.0
• max_steps: 100
• 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: 30
• 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: True
• 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
• 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: 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: no_duplicates
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	all-nli-val-1024_cosine_accuracy	all-nli-val-768_cosine_accuracy	all-nli-val-512_cosine_accuracy	all-nli-val-256_cosine_accuracy	all-nli-val-128_cosine_accuracy	all-nli-val-64_cosine_accuracy	all-nli-test-1024_cosine_accuracy	all-nli-test-768_cosine_accuracy	all-nli-test-512_cosine_accuracy	all-nli-test-256_cosine_accuracy	all-nli-test-128_cosine_accuracy	all-nli-test-64_cosine_accuracy
0.0025	100	2.4168	1.292	0.9507	0.9497	0.9477	0.9453	0.9393	0.931	-	-	-	-	-	-
-1	-1	-	-	-	-	-	-	-	-	0.9532	0.9516	0.9504	0.9493	0.9452	0.9363

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.12.11
• Sentence Transformers: 5.1.0
• Transformers: 4.56.1
• PyTorch: 2.8.0+cu126
• Accelerate: 1.10.1
• Datasets: 4.0.0
• Tokenizers: 0.22.0

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",
}

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}
}