waris-gill/ModernBert-Medical-v1

SentenceTransformer based on Alibaba-NLP/gte-modernbert-base

This is a sentence-transformers model finetuned from Alibaba-NLP/gte-modernbert-base on the csv dataset. 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: Alibaba-NLP/gte-modernbert-base
• Maximum Sequence Length: 8192 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • csv

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': 8192, 'do_lower_case': False}) with Transformer model: ModernBertModel 
  (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})
)

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("waris-gill/ModernBert-Medical-v1")
# Run inference
sentences = [
    'My rheumatologist said \'if a patient has lupus then prednisone doesn\'t work." why is that?',
    "I have lupus,my rheumatologist told me that prednisone doesn't work in my case. Could you educate me why? What are my chances? ",
    'Hello doctor, my grandmother has 3rd degree bed sore. What can be done to help?',
]
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

My Binary Classification

• Evaluated with scache.train.MyBinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.916
cosine_accuracy_threshold	0.8091
cosine_f1	0.9216
cosine_f1_threshold	0.8091
cosine_precision	0.9305
cosine_recall	0.9129
cosine_ap	0.9742
cosine_mcc	0.8313

Training Details

Training Dataset

csv

• Dataset: csv

• Size: 2,438 training samples

• Columns: question_1, question_2, and label

• Approximate statistics based on the first 1000 samples:

• Loss: MatryoshkaLoss with these parameters:

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

Evaluation Dataset

csv

• Dataset: csv
• Size: 2,438 evaluation samples

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 256
• learning_rate: 6.5383156211679e-05
• max_grad_norm: 0.5
• num_train_epochs: 1
• lr_scheduler_type: constant
• load_best_model_at_end: True
• torch_compile: True
• torch_compile_backend: inductor
• 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: 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: 6.5383156211679e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 0.5
• num_train_epochs: 1
• max_steps: -1
• lr_scheduler_type: constant
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• 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: 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}
• 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: None
• hub_always_push: False
• 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: True
• torch_compile_backend: inductor
• 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
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	cosine_ap
0.0323	1	4.4977	-	-
0.0645	2	4.9952	-	-
0.0968	3	2.9984	-	-
0.1290	4	4.8052	-	-
0.1613	5	4.0031	-	-
0.1935	6	3.7682	-	-
0.2258	7	4.0361	-	-
0.2581	8	3.4003	-	-
0.2903	9	1.1674	-	-
0.3226	10	2.3826	14.3756	0.9742
0.3548	11	3.8777	-	-
0.3871	12	2.6367	-	-
0.4194	13	2.5763	-	-
0.4516	14	3.5591	-	-
0.4839	15	2.3568	-	-
0.5161	16	2.9432	-	-
0.5484	17	2.746	-	-
0.5806	18	3.647	-	-
0.6129	19	3.0907	-	-
0.6452	20	3.9776	12.4766	0.9771
0.6774	21	3.4131	-	-
0.7097	22	3.0084	-	-
0.7419	23	2.7182	-	-
0.7742	24	1.5211	-	-
0.8065	25	1.8332	-	-
0.8387	26	3.4883	-	-
0.8710	27	2.0585	-	-
0.9032	28	2.775	-	-
0.9355	29	2.9137	-	-
0.9677	30	2.4238	12.4805	0.9769
1.0	31	1.2115	14.3756	0.9742

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.11.11
• Sentence Transformers: 3.4.1
• Transformers: 4.49.0
• PyTorch: 2.5.1+cu124
• Accelerate: 1.4.0
• Datasets: 3.3.2
• Tokenizers: 0.21.0

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",
}