all-MiniLM-L6-v18-pair_score

This is a sentence-transformers model finetuned from youssefkhalil320/all-MiniLM-L6-v14-pair_score. 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: youssefkhalil320/all-MiniLM-L6-v14-pair_score
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 384 tokens
• Similarity Function: Cosine Similarity
• Language: en
• License: apache-2.0

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}) 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})
  (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("sentence_transformers_model_id")
# Run inference
sentences = [
    'medical accessory',
    'bedroom chair',
    'handball',
]
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]

Training Details

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 128
• per_device_eval_batch_size: 128
• learning_rate: 2e-05
• num_train_epochs: 2
• warmup_ratio: 0.1
• 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: 128
• per_device_eval_batch_size: 128
• 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: 2
• 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
• use_liger_kernel: False
• eval_use_gather_object: False
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss
0.0244	100	15.2955
0.0488	200	12.0245
0.0732	300	9.5958
0.0977	400	9.0251
0.1221	500	8.8519
0.1465	600	8.7625
0.1709	700	8.7085
0.1953	800	8.6742
0.2197	900	8.6344
0.2441	1000	8.5984
0.2686	1100	8.5607
0.2930	1200	8.5395
0.3174	1300	8.4973
0.3418	1400	8.4809
0.3662	1500	8.4588
0.3906	1600	8.4489
0.4150	1700	8.4255
0.4395	1800	8.4189
0.4639	1900	8.4012
0.4883	2000	8.3793
0.5127	2100	8.3654
0.5371	2200	8.3369
0.5615	2300	8.3483
0.5859	2400	8.3441
0.6104	2500	8.3357
0.6348	2600	8.3009
0.6592	2700	8.2997
0.6836	2800	8.2901
0.7080	2900	8.2797
0.7324	3000	8.2837
0.7568	3100	8.2856
0.7812	3200	8.2753
0.8057	3300	8.275
0.8301	3400	8.2577
0.8545	3500	8.2296
0.8789	3600	8.2368
0.9033	3700	8.244
0.9277	3800	8.2259
0.9521	3900	8.2262
0.9766	4000	8.252
1.0010	4100	8.1966
1.0254	4200	8.1923
1.0498	4300	8.1938
1.0742	4400	8.1771
1.0986	4500	8.1956
1.1230	4600	8.1826
1.1475	4700	8.1726
1.1719	4800	8.1826
1.1963	4900	8.1699
1.2207	5000	8.1576
1.2451	5100	8.1849
1.2695	5200	8.1753
1.2939	5300	8.1661
1.3184	5400	8.153
1.3428	5500	8.158
1.3672	5600	8.1577
1.3916	5700	8.152
1.4160	5800	8.1716
1.4404	5900	8.1528
1.4648	6000	8.1561
1.4893	6100	8.1658
1.5137	6200	8.1379
1.5381	6300	8.1437
1.5625	6400	8.1329
1.5869	6500	8.1251
1.6113	6600	8.1359
1.6357	6700	8.1334
1.6602	6800	8.1187
1.6846	6900	8.1461
1.7090	7000	8.1294
1.7334	7100	8.0935
1.7578	7200	8.1494
1.7822	7300	8.105
1.8066	7400	8.0987
1.8311	7500	8.1524
1.8555	7600	8.1228
1.8799	7700	8.1228
1.9043	7800	8.1315
1.9287	7900	8.1236
1.9531	8000	8.1499
1.9775	8100	8.1092

Framework Versions

• Python: 3.8.10
• Sentence Transformers: 3.1.1
• Transformers: 4.45.2
• PyTorch: 2.4.1+cu118
• Accelerate: 1.0.1
• Datasets: 3.0.1
• Tokenizers: 0.20.3

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",
}

CoSENTLoss

@online{kexuefm-8847,
    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
    author={Su Jianlin},
    year={2022},
    month={Jan},
    url={https://kexue.fm/archives/8847},
}