Hugging Face's logo

BotnoiNLPteam
/
me5_icd10_test

Sentence Similarity
sentence-transformers
Safetensors
xlm-roberta
feature-extraction
Generated from Trainer
dataset_size:36755
loss:MatryoshkaLoss
loss:MultipleNegativesRankingLoss
Eval Results
Inference Endpoints
text-embeddings-inference
Model card Files Community
Edit model card

SentenceTransformer based on intfloat/multilingual-e5-base

This is a sentence-transformers model finetuned from intfloat/multilingual-e5-base. 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: intfloat/multilingual-e5-base
  • Maximum Sequence Length: 512 tokens
  • Output Dimensionality: 768 tokens
  • Similarity Function: Cosine Similarity

Model Sources

Full Model Architecture 

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 768, '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("BotnoiNLPteam/me5_icd10_test")
# Run inference
sentences = [
    'Contact with other powered hand tools and household machinery at residential institution While engaged in leisure activity',
    'สัมผัสกับเครื่องมือที่มีเครื่องยนต์และเครื่องจักรกลอื่นในบ้าน ที่พักอาศัยรวมขณะทำกิจกรรมยามว่าง',
    'หลอดเลือดอักเสบรูมาตอยด์',
]
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

Metric Value
cosine_accuracy@1 0.8761
cosine_accuracy@3 0.9407
cosine_accuracy@5 0.9569
cosine_accuracy@10 0.9718
cosine_precision@1 0.8761
cosine_precision@3 0.3136
cosine_precision@5 0.1914
cosine_precision@10 0.0972
cosine_recall@1 0.8761
cosine_recall@3 0.9407
cosine_recall@5 0.9569
cosine_recall@10 0.9718
cosine_ndcg@10 0.9264
cosine_mrr@10 0.9115
cosine_map@100 0.9127

Information Retrieval

Metric Value
cosine_accuracy@1 0.8768
cosine_accuracy@3 0.94
cosine_accuracy@5 0.9576
cosine_accuracy@10 0.9716
cosine_precision@1 0.8768
cosine_precision@3 0.3133
cosine_precision@5 0.1915
cosine_precision@10 0.0972
cosine_recall@1 0.8768
cosine_recall@3 0.94
cosine_recall@5 0.9576
cosine_recall@10 0.9716
cosine_ndcg@10 0.9265
cosine_mrr@10 0.9118
cosine_map@100 0.913

Information Retrieval

Metric Value
cosine_accuracy@1 0.8761
cosine_accuracy@3 0.9376
cosine_accuracy@5 0.9557
cosine_accuracy@10 0.9714
cosine_precision@1 0.8761
cosine_precision@3 0.3125
cosine_precision@5 0.1911
cosine_precision@10 0.0971
cosine_recall@1 0.8761
cosine_recall@3 0.9376
cosine_recall@5 0.9557
cosine_recall@10 0.9714
cosine_ndcg@10 0.9257
cosine_mrr@10 0.9109
cosine_map@100 0.9121

Information Retrieval

Metric Value
cosine_accuracy@1 0.8705
cosine_accuracy@3 0.9366
cosine_accuracy@5 0.9537
cosine_accuracy@10 0.9711
cosine_precision@1 0.8705
cosine_precision@3 0.3122
cosine_precision@5 0.1907
cosine_precision@10 0.0971
cosine_recall@1 0.8705
cosine_recall@3 0.9366
cosine_recall@5 0.9537
cosine_recall@10 0.9711
cosine_ndcg@10 0.923
cosine_mrr@10 0.9073
cosine_map@100 0.9086

Information Retrieval

Metric Value
cosine_accuracy@1 0.8666
cosine_accuracy@3 0.9329
cosine_accuracy@5 0.9503
cosine_accuracy@10 0.9709
cosine_precision@1 0.8666
cosine_precision@3 0.311
cosine_precision@5 0.1901
cosine_precision@10 0.0971
cosine_recall@1 0.8666
cosine_recall@3 0.9329
cosine_recall@5 0.9503
cosine_recall@10 0.9709
cosine_ndcg@10 0.921
cosine_mrr@10 0.9048
cosine_map@100 0.9059

Training Details

Training Hyperparameters

Non-Default Hyperparameters

  • eval_strategy: epoch
  • per_device_train_batch_size: 16
  • per_device_eval_batch_size: 16
  • num_train_epochs: 5
  • warmup_ratio: 0.1
  • bf16: True
  • batch_sampler: no_duplicates

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: epoch
  • 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: 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: 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
  • batch_sampler: no_duplicates
  • multi_dataset_batch_sampler: proportional

Training Logs

Epoch Step Training Loss 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
0.4352 1000 0.5774 - - - - -
0.8703 2000 0.0914 - - - - -
1.0 2298 - 0.8254 0.8378 0.8427 0.8159 0.8439
1.3055 3000 0.0486 - - - - -
1.7406 4000 0.018 - - - - -
2.0 4596 - 0.8674 0.8731 0.8756 0.8615 0.8781
2.1758 5000 0.0123 - - - - -
2.6110 6000 0.0047 - - - - -
3.0 6894 - 0.8908 0.8940 0.8952 0.8868 0.8959
3.0461 7000 0.0031 - - - - -
3.4813 8000 0.0013 - - - - -
3.9164 9000 0.0012 - - - - -
4.0 9192 - 0.9049 0.9065 0.9075 0.8999 0.9079
4.3516 10000 0.0005 - - - - -
4.7868 11000 0.0002 - - - - -
5.0 11490 - 0.9086 0.9121 0.9130 0.9059 0.9127

Framework Versions

  • Python: 3.8.10
  • Sentence Transformers: 3.0.1
  • Transformers: 4.42.0.dev0
  • PyTorch: 2.3.0+cu121
  • Accelerate: 0.30.1
  • Datasets: 2.19.1
  • 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",
}

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}
}
Downloads last month
91
Safetensors
Model size
278M params
Tensor type
F32
·

Finetuned from

Evaluation results

View on Papers With Code