vineet10/fm1

SentenceTransformer based on BAAI/bge-base-en-v1.5

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5. It maps sentences & paragraphs to a 768-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-base-en-v1.5
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 tokens
• 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': 512, 'do_lower_case': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, '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
model = SentenceTransformer("vineet10/fm1")
# Run inference
sentences = [
    'This Agreement shall be governed by and construed in accordance with the laws of Indiana. Any dispute arising out of or in connection with this Agreement shall be resolved through good faith negotiations between the Parties and will be subject to the jurisdiction of the courts of Dania.',
    'Under which laws is the Battery Supply Agreement governed and how are disputes resolved?',
    'What events constitute Force Majeure under this Agreement?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

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

Evaluation

Metrics

Information Retrieval

• Dataset: dim_768
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8333
cosine_accuracy@3	0.8333
cosine_accuracy@5	0.8333
cosine_accuracy@10	1.0
cosine_precision@1	0.8333
cosine_precision@3	0.2778
cosine_precision@5	0.1667
cosine_precision@10	0.1
cosine_recall@1	0.8333
cosine_recall@3	0.8333
cosine_recall@5	0.8333
cosine_recall@10	1.0
cosine_ndcg@10	0.8927
cosine_mrr@10	0.8611
cosine_map@100	0.8611

Information Retrieval

• Dataset: dim_512
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8333
cosine_accuracy@3	0.8333
cosine_accuracy@5	0.8333
cosine_accuracy@10	1.0
cosine_precision@1	0.8333
cosine_precision@3	0.2778
cosine_precision@5	0.1667
cosine_precision@10	0.1
cosine_recall@1	0.8333
cosine_recall@3	0.8333
cosine_recall@5	0.8333
cosine_recall@10	1.0
cosine_ndcg@10	0.8927
cosine_mrr@10	0.8611
cosine_map@100	0.8611

Information Retrieval

• Dataset: dim_256
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8333
cosine_accuracy@3	0.8333
cosine_accuracy@5	0.8333
cosine_accuracy@10	1.0
cosine_precision@1	0.8333
cosine_precision@3	0.2778
cosine_precision@5	0.1667
cosine_precision@10	0.1
cosine_recall@1	0.8333
cosine_recall@3	0.8333
cosine_recall@5	0.8333
cosine_recall@10	1.0
cosine_ndcg@10	0.8927
cosine_mrr@10	0.8611
cosine_map@100	0.8611

Information Retrieval

• Dataset: dim_128
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8333
cosine_accuracy@3	0.8333
cosine_accuracy@5	0.8333
cosine_accuracy@10	1.0
cosine_precision@1	0.8333
cosine_precision@3	0.2778
cosine_precision@5	0.1667
cosine_precision@10	0.1
cosine_recall@1	0.8333
cosine_recall@3	0.8333
cosine_recall@5	0.8333
cosine_recall@10	1.0
cosine_ndcg@10	0.8859
cosine_mrr@10	0.8542
cosine_map@100	0.8542

Information Retrieval

• Dataset: dim_64
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8333
cosine_accuracy@3	0.8333
cosine_accuracy@5	0.8333
cosine_accuracy@10	1.0
cosine_precision@1	0.8333
cosine_precision@3	0.2778
cosine_precision@5	0.1667
cosine_precision@10	0.1
cosine_recall@1	0.8333
cosine_recall@3	0.8333
cosine_recall@5	0.8333
cosine_recall@10	1.0
cosine_ndcg@10	0.8835
cosine_mrr@10	0.8519
cosine_map@100	0.8519

Training Details

Training Dataset

Unnamed Dataset

• Size: 48 training samples
• Columns: context and question
• Approximate statistics based on the first 1000 samples:

  	context	question
  type	string	string
  details	min: 18 tokens mean: 39.58 tokens max: 85 tokens	min: 8 tokens mean: 17.9 tokens max: 32 tokens

• Samples:

  context	question
  The Client will pay a flat fee of Rs. 52,000/-, with 50% (Rs. 26,000/-) due upon signing the agreement and the remaining 50% due one week after completion of pre-production. Payment delays will result in proportional delays in data delivery and editing.	What are the specified payment terms for the photography services under this contract?
  Users can report delays to Customer Care and expect an automatic refund within 3-4 business days if services are canceled or rescheduled by the platform.	What actions can a user take if the platform is unable to fulfill a successfully placed order?
  Signed by James Hira, Managing Director of Electric Vehicle Battery Supplier Pvt. Ltd, and Managing Director of Best Car Manufacturer Pvt. Ltd	Who signed the Battery Supply Agreement on behalf of the Supplier and the Manufacturer?

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• num_train_epochs: 5
• warmup_ratio: 0.1
• fp16: 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: 16
• per_device_eval_batch_size: 16
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• learning_rate: 5e-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: 5
• 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: 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: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	dim_128_cosine_map@100	dim_256_cosine_map@100	dim_512_cosine_map@100	dim_64_cosine_map@100	dim_768_cosine_map@100
0	0	0.8542	0.8611	0.8611	0.8519	0.8611

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.0.1
• Transformers: 4.42.4
• PyTorch: 2.3.1+cu121
• Accelerate: 0.32.1
• Datasets: 2.20.0
• 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}
}