| | --- |
| | tags: |
| | - sentence-transformers |
| | - sentence-similarity |
| | - feature-extraction |
| | - dense |
| | - generated_from_trainer |
| | - dataset_size:329355 |
| | - loss:MultipleNegativesRankingLoss |
| | base_model: NeuML/pubmedbert-base-embeddings |
| | widget: |
| | - source_sentence: 'CONTEXT: check your other micronutrients B12, folate, your vitamin |
| | D malabsorbed after surgery |
| | |
| | REASONING: Folate listed among micronutrients to check.' |
| | sentences: |
| | - XR FOOT LT 3 View* (HUD) |
| | - Folate, Serum (Request)* (Orchard) |
| | - Wound Cleansing/Irrigation, Clinic |
| | - source_sentence: 'COMMAND: Submit a 99213 established patient office visit charge |
| | for today’s evaluation and counseling.' |
| | sentences: |
| | - '[''99213 office o/p est low 20-29 min (Charge)''' |
| | - 99213 office o/p est low 20-29 min (Charge) |
| | - clotrimazole 1% topical cream |
| | - source_sentence: 'CONTEXT: pediatric patient with fever, sore throat, headache exam |
| | of ears, throat, lungs; counseling on strep care school note discussed; pharmacy |
| | confirmed; results to be called' |
| | sentences: |
| | - meloxicam 7.5 mg oral tablet |
| | - 99213 office o/p est low 20-29 min (Charge) |
| | - 99214 office o/p est mod 30-39 min (Charge) |
| | - source_sentence: 'CONTEXT: established patient follow-up style visit anxiety, tremor |
| | assessment and medication counseling 30–40 minute detailed discussion management |
| | options and side effects reviewed |
| | |
| | REASONING: Extended medical decision-making on anxiety and essential tremor with |
| | medication options and counseling consistent with a moderate complexity, mid-length |
| | established patient visit.' |
| | sentences: |
| | - 99214 office o/p est mod 30-39 min (Charge) |
| | - '''A4550 surgical trays (Charge)''' |
| | - '[''99214 office o/p est mod 30-39 min (Charge)'']' |
| | - source_sentence: 'COMMAND: Have lab draw blood today per ordered tests. |
| | |
| | CONTEXT: get a little blood work today they''re gonna get you to x-ray and lab |
| | before you leave' |
| | sentences: |
| | - Thin Prep Pap w/ High Risk HPV, Over 30 Years old (Request)* (Orchard) |
| | - Rocephin* |
| | - 36415 blood draw, venipuncture (Charge) |
| | pipeline_tag: sentence-similarity |
| | library_name: sentence-transformers |
| | --- |
| | |
| | # SentenceTransformer based on NeuML/pubmedbert-base-embeddings |
| |
|
| | This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [NeuML/pubmedbert-base-embeddings](https://huggingface.co/NeuML/pubmedbert-base-embeddings). 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:** [NeuML/pubmedbert-base-embeddings](https://huggingface.co/NeuML/pubmedbert-base-embeddings) <!-- at revision d6eaca8254bc229f3ca42749a5510ae287eb3486 --> |
| | - **Maximum Sequence Length:** 512 tokens |
| | - **Output Dimensionality:** 768 dimensions |
| | - **Similarity Function:** Cosine Similarity |
| | <!-- - **Training Dataset:** Unknown --> |
| | <!-- - **Language:** Unknown --> |
| | <!-- - **License:** Unknown --> |
| |
|
| | ### Model Sources |
| |
|
| | - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) |
| | - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) |
| | - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) |
| |
|
| | ### Full Model Architecture |
| |
|
| | ``` |
| | SentenceTransformer( |
| | (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'BertModel'}) |
| | (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}) |
| | ) |
| | ``` |
| |
|
| | ## Usage |
| |
|
| | ### Direct Usage (Sentence Transformers) |
| |
|
| | First install the Sentence Transformers library: |
| |
|
| | ```bash |
| | pip install -U sentence-transformers |
| | ``` |
| |
|
| | Then you can load this model and run inference. |
| | ```python |
| | from sentence_transformers import SentenceTransformer |
| | |
| | # Download from the 🤗 Hub |
| | model = SentenceTransformer("praphul555/jeda-stage-1") |
| | # Run inference |
| | sentences = [ |
| | "COMMAND: Have lab draw blood today per ordered tests.\nCONTEXT: get a little blood work today they're gonna get you to x-ray and lab before you leave", |
| | 'blood draw, venipuncture (Charge)', |
| | 'Rocephin*', |
| | ] |
| | embeddings = model.encode(sentences) |
| | print(embeddings.shape) |
| | # [3, 768] |
| | |
| | # Get the similarity scores for the embeddings |
| | similarities = model.similarity(embeddings, embeddings) |
| | print(similarities) |
| | # tensor([[ 1.0000, 0.8369, -0.0363], |
| | # [ 0.8369, 1.0000, -0.0708], |
| | # [-0.0363, -0.0708, 1.0000]]) |
| | ``` |
| |
|
| | <!-- |
| | ### Direct Usage (Transformers) |
| |
|
| | <details><summary>Click to see the direct usage in Transformers</summary> |
| |
|
| | </details> |
| | --> |
| |
|
| | <!-- |
| | ### Downstream Usage (Sentence Transformers) |
| |
|
| | You can finetune this model on your own dataset. |
| |
|
| | <details><summary>Click to expand</summary> |
| |
|
| | </details> |
| | --> |
| |
|
| | <!-- |
| | ### Out-of-Scope Use |
| |
|
| | *List how the model may foreseeably be misused and address what users ought not to do with the model.* |
| | --> |
| |
|
| | <!-- |
| | ## Bias, Risks and Limitations |
| |
|
| | *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* |
| | --> |
| |
|
| | <!-- |
| | ### Recommendations |
| |
|
| | *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* |
| | --> |
| |
|
| | ## Training Details |
| |
|
| | ### Training Dataset |
| |
|
| | #### Unnamed Dataset |
| |
|
| | * Size: 329,355 training samples |
| | * Columns: <code>text1</code> and <code>text2</code> |
| | * Approximate statistics based on the first 1000 samples: |
| | | | text1 | text2 | |
| | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| |
| | | type | string | string | |
| | | details | <ul><li>min: 8 tokens</li><li>mean: 37.3 tokens</li><li>max: 106 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 12.95 tokens</li><li>max: 24 tokens</li></ul> | |
| | * Samples: |
| | | text1 | text2 | |
| | |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------| |
| | | <code>COMMAND: Please arrange transport to radiology now and let them know we're sending him for a right foot/toe x-ray with weight-bearing views.<br>CONTEXT: wheel him over to x-ray x-ray right foot complete with weight-bearing views go tell the x-ray lady</code> | <code>Radiology Transfer Communication</code> | |
| | | <code>COMMAND: Please arrange transport to radiology now and let them know we're sending him for a right foot/toe x-ray with weight-bearing views.</code> | <code>Radiology Transfer Communication</code> | |
| | | <code>CONTEXT: wheel him over to x-ray x-ray right foot complete with weight-bearing views go tell the x-ray lady<br>REASONING: Doctor instructs staff to transport patient to x-ray and communicate exam details.</code> | <code>Radiology Transfer Communication</code> | |
| | * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: |
| | ```json |
| | { |
| | "scale": 20.0, |
| | "similarity_fct": "cos_sim" |
| | } |
| | ``` |
| |
|
| | ### Training Hyperparameters |
| | #### Non-Default Hyperparameters |
| |
|
| | - `per_device_train_batch_size`: 64 |
| | - `learning_rate`: 2e-05 |
| | - `num_train_epochs`: 5 |
| | - `warmup_ratio`: 0.1 |
| | - `seed`: 13 |
| | - `batch_sampler`: no_duplicates |
| | |
| | #### All Hyperparameters |
| | <details><summary>Click to expand</summary> |
| | |
| | - `overwrite_output_dir`: False |
| | - `do_predict`: False |
| | - `eval_strategy`: no |
| | - `prediction_loss_only`: True |
| | - `per_device_train_batch_size`: 64 |
| | - `per_device_eval_batch_size`: 8 |
| | - `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`: 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`: 13 |
| | - `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`: 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} |
| | - `parallelism_config`: 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 |
| | - `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`: {} |
| |
|
| | </details> |
| |
|
| | ### Training Logs |
| | <details><summary>Click to expand</summary> |
| |
|
| | | Epoch | Step | Training Loss | |
| | |:------:|:-----:|:-------------:| |
| | | 0.0097 | 50 | 2.3103 | |
| | | 0.0194 | 100 | 1.9798 | |
| | | 0.0291 | 150 | 1.6487 | |
| | | 0.0389 | 200 | 1.3829 | |
| | | 0.0486 | 250 | 1.25 | |
| | | 0.0583 | 300 | 1.1482 | |
| | | 0.0680 | 350 | 1.0997 | |
| | | 0.0777 | 400 | 1.0484 | |
| | | 0.0874 | 450 | 0.9522 | |
| | | 0.0971 | 500 | 0.9385 | |
| | | 0.1069 | 550 | 0.8914 | |
| | | 0.1166 | 600 | 0.86 | |
| | | 0.1263 | 650 | 0.8825 | |
| | | 0.1360 | 700 | 0.8217 | |
| | | 0.1457 | 750 | 0.8102 | |
| | | 0.1554 | 800 | 0.7831 | |
| | | 0.1651 | 850 | 0.796 | |
| | | 0.1749 | 900 | 0.7542 | |
| | | 0.1846 | 950 | 0.775 | |
| | | 0.1943 | 1000 | 0.7437 | |
| | | 0.2040 | 1050 | 0.7237 | |
| | | 0.2137 | 1100 | 0.6945 | |
| | | 0.2234 | 1150 | 0.6979 | |
| | | 0.2331 | 1200 | 0.6834 | |
| | | 0.2429 | 1250 | 0.7149 | |
| | | 0.2526 | 1300 | 0.6582 | |
| | | 0.2623 | 1350 | 0.6437 | |
| | | 0.2720 | 1400 | 0.6213 | |
| | | 0.2817 | 1450 | 0.6087 | |
| | | 0.2914 | 1500 | 0.6225 | |
| | | 0.3011 | 1550 | 0.5579 | |
| | | 0.3109 | 1600 | 0.6206 | |
| | | 0.3206 | 1650 | 0.5787 | |
| | | 0.3303 | 1700 | 0.5721 | |
| | | 0.3400 | 1750 | 0.5695 | |
| | | 0.3497 | 1800 | 0.5395 | |
| | | 0.3594 | 1850 | 0.5476 | |
| | | 0.3691 | 1900 | 0.5556 | |
| | | 0.3789 | 1950 | 0.5628 | |
| | | 0.3886 | 2000 | 0.5241 | |
| | | 0.3983 | 2050 | 0.5457 | |
| | | 0.4080 | 2100 | 0.5339 | |
| | | 0.4177 | 2150 | 0.5429 | |
| | | 0.4274 | 2200 | 0.5421 | |
| | | 0.4371 | 2250 | 0.5149 | |
| | | 0.4469 | 2300 | 0.5015 | |
| | | 0.4566 | 2350 | 0.5005 | |
| | | 0.4663 | 2400 | 0.5149 | |
| | | 0.4760 | 2450 | 0.5004 | |
| | | 0.4857 | 2500 | 0.4852 | |
| | | 0.4954 | 2550 | 0.5316 | |
| | | 0.5051 | 2600 | 0.5227 | |
| | | 0.5149 | 2650 | 0.5138 | |
| | | 0.5246 | 2700 | 0.4744 | |
| | | 0.5343 | 2750 | 0.4885 | |
| | | 0.5440 | 2800 | 0.5036 | |
| | | 0.5537 | 2850 | 0.5077 | |
| | | 0.5634 | 2900 | 0.4669 | |
| | | 0.5731 | 2950 | 0.4682 | |
| | | 0.5829 | 3000 | 0.4588 | |
| | | 0.5926 | 3050 | 0.4567 | |
| | | 0.6023 | 3100 | 0.4671 | |
| | | 0.6120 | 3150 | 0.5114 | |
| | | 0.6217 | 3200 | 0.4715 | |
| | | 0.6314 | 3250 | 0.4353 | |
| | | 0.6412 | 3300 | 0.46 | |
| | | 0.6509 | 3350 | 0.4525 | |
| | | 0.6606 | 3400 | 0.4633 | |
| | | 0.6703 | 3450 | 0.4344 | |
| | | 0.6800 | 3500 | 0.4566 | |
| | | 0.6897 | 3550 | 0.4643 | |
| | | 0.6994 | 3600 | 0.4615 | |
| | | 0.7092 | 3650 | 0.4387 | |
| | | 0.7189 | 3700 | 0.4145 | |
| | | 0.7286 | 3750 | 0.4646 | |
| | | 0.7383 | 3800 | 0.4831 | |
| | | 0.7480 | 3850 | 0.444 | |
| | | 0.7577 | 3900 | 0.4412 | |
| | | 0.7674 | 3950 | 0.4407 | |
| | | 0.7772 | 4000 | 0.4383 | |
| | | 0.7869 | 4050 | 0.4403 | |
| | | 0.7966 | 4100 | 0.4674 | |
| | | 0.8063 | 4150 | 0.4477 | |
| | | 0.8160 | 4200 | 0.4619 | |
| | | 0.8257 | 4250 | 0.4368 | |
| | | 0.8354 | 4300 | 0.4531 | |
| | | 0.8452 | 4350 | 0.4409 | |
| | | 0.8549 | 4400 | 0.4456 | |
| | | 0.8646 | 4450 | 0.4312 | |
| | | 0.8743 | 4500 | 0.4233 | |
| | | 0.8840 | 4550 | 0.4134 | |
| | | 0.8937 | 4600 | 0.3193 | |
| | | 0.9034 | 4650 | 0.2839 | |
| | | 0.9132 | 4700 | 0.2286 | |
| | | 0.9229 | 4750 | 0.2572 | |
| | | 0.9326 | 4800 | 0.2896 | |
| | | 0.9423 | 4850 | 0.1615 | |
| | | 0.9520 | 4900 | 0.2984 | |
| | | 0.9617 | 4950 | 0.1891 | |
| | | 0.9714 | 5000 | 0.2552 | |
| | | 0.9812 | 5050 | 0.2165 | |
| | | 0.9909 | 5100 | 0.2774 | |
| | | 1.0006 | 5150 | 0.2737 | |
| | | 1.0103 | 5200 | 0.447 | |
| | | 1.0200 | 5250 | 0.4317 | |
| | | 1.0297 | 5300 | 0.3798 | |
| | | 1.0394 | 5350 | 0.4063 | |
| | | 1.0492 | 5400 | 0.4231 | |
| | | 1.0589 | 5450 | 0.4202 | |
| | | 1.0686 | 5500 | 0.3911 | |
| | | 1.0783 | 5550 | 0.3807 | |
| | | 1.0880 | 5600 | 0.3979 | |
| | | 1.0977 | 5650 | 0.3908 | |
| | | 1.1074 | 5700 | 0.4167 | |
| | | 1.1172 | 5750 | 0.3885 | |
| | | 1.1269 | 5800 | 0.3992 | |
| | | 1.1366 | 5850 | 0.4102 | |
| | | 1.1463 | 5900 | 0.3949 | |
| | | 1.1560 | 5950 | 0.4066 | |
| | | 1.1657 | 6000 | 0.3871 | |
| | | 1.1754 | 6050 | 0.3925 | |
| | | 1.1852 | 6100 | 0.3785 | |
| | | 1.1949 | 6150 | 0.4529 | |
| | | 1.2046 | 6200 | 0.4188 | |
| | | 1.2143 | 6250 | 0.4844 | |
| | | 1.2240 | 6300 | 0.4171 | |
| | | 1.2337 | 6350 | 0.4001 | |
| | | 1.2434 | 6400 | 0.3992 | |
| | | 1.2532 | 6450 | 0.4167 | |
| | | 1.2629 | 6500 | 0.4395 | |
| | | 1.2726 | 6550 | 0.4 | |
| | | 1.2823 | 6600 | 0.3905 | |
| | | 1.2920 | 6650 | 0.3769 | |
| | | 1.3017 | 6700 | 0.3846 | |
| | | 1.3114 | 6750 | 0.4 | |
| | | 1.3212 | 6800 | 0.4062 | |
| | | 1.3309 | 6850 | 0.3972 | |
| | | 1.3406 | 6900 | 0.3875 | |
| | | 1.3503 | 6950 | 0.3958 | |
| | | 1.3600 | 7000 | 0.3843 | |
| | | 1.3697 | 7050 | 0.4004 | |
| | | 1.3794 | 7100 | 0.4435 | |
| | | 1.3892 | 7150 | 0.3856 | |
| | | 1.3989 | 7200 | 0.3843 | |
| | | 1.4086 | 7250 | 0.3777 | |
| | | 1.4183 | 7300 | 0.4103 | |
| | | 1.4280 | 7350 | 0.3795 | |
| | | 1.4377 | 7400 | 0.3719 | |
| | | 1.4474 | 7450 | 0.3938 | |
| | | 1.4572 | 7500 | 0.4058 | |
| | | 1.4669 | 7550 | 0.3913 | |
| | | 1.4766 | 7600 | 0.3992 | |
| | | 1.4863 | 7650 | 0.3743 | |
| | | 1.4960 | 7700 | 0.4072 | |
| | | 1.5057 | 7750 | 0.3788 | |
| | | 1.5154 | 7800 | 0.3987 | |
| | | 1.5252 | 7850 | 0.3774 | |
| | | 1.5349 | 7900 | 0.3803 | |
| | | 1.5446 | 7950 | 0.3582 | |
| | | 1.5543 | 8000 | 0.4222 | |
| | | 1.5640 | 8050 | 0.4001 | |
| | | 1.5737 | 8100 | 0.3857 | |
| | | 1.5834 | 8150 | 0.3819 | |
| | | 1.5932 | 8200 | 0.3643 | |
| | | 1.6029 | 8250 | 0.3884 | |
| | | 1.6126 | 8300 | 0.3761 | |
| | | 1.6223 | 8350 | 0.4295 | |
| | | 1.6320 | 8400 | 0.4073 | |
| | | 1.6417 | 8450 | 0.3963 | |
| | | 1.6514 | 8500 | 0.389 | |
| | | 1.6612 | 8550 | 0.3677 | |
| | | 1.6709 | 8600 | 0.4012 | |
| | | 1.6806 | 8650 | 0.3732 | |
| | | 1.6903 | 8700 | 0.3793 | |
| | | 1.7000 | 8750 | 0.3712 | |
| | | 1.7097 | 8800 | 0.3734 | |
| | | 1.7194 | 8850 | 0.3895 | |
| | | 1.7292 | 8900 | 0.3667 | |
| | | 1.7389 | 8950 | 0.3832 | |
| | | 1.7486 | 9000 | 0.3842 | |
| | | 1.7583 | 9050 | 0.3822 | |
| | | 1.7680 | 9100 | 0.3706 | |
| | | 1.7777 | 9150 | 0.3699 | |
| | | 1.7874 | 9200 | 0.3738 | |
| | | 1.7972 | 9250 | 0.3748 | |
| | | 1.8069 | 9300 | 0.3911 | |
| | | 1.8166 | 9350 | 0.366 | |
| | | 1.8263 | 9400 | 0.3626 | |
| | | 1.8360 | 9450 | 0.3762 | |
| | | 1.8457 | 9500 | 0.3711 | |
| | | 1.8554 | 9550 | 0.3568 | |
| | | 1.8652 | 9600 | 0.3877 | |
| | | 1.8749 | 9650 | 0.3744 | |
| | | 1.8846 | 9700 | 0.3858 | |
| | | 1.8943 | 9750 | 0.2191 | |
| | | 1.9040 | 9800 | 0.1622 | |
| | | 1.9137 | 9850 | 0.13 | |
| | | 1.9235 | 9900 | 0.359 | |
| | | 1.9332 | 9950 | 0.1739 | |
| | | 1.9429 | 10000 | 0.2212 | |
| | | 1.9526 | 10050 | 0.2445 | |
| | | 1.9623 | 10100 | 0.2059 | |
| | | 1.9720 | 10150 | 0.2288 | |
| | | 1.9817 | 10200 | 0.1985 | |
| | | 1.9915 | 10250 | 0.182 | |
| | | 2.0012 | 10300 | 0.2609 | |
| | | 2.0109 | 10350 | 0.3533 | |
| | | 2.0206 | 10400 | 0.3322 | |
| | | 2.0303 | 10450 | 0.3565 | |
| | | 2.0400 | 10500 | 0.3454 | |
| | | 2.0497 | 10550 | 0.3623 | |
| | | 2.0595 | 10600 | 0.3685 | |
| | | 2.0692 | 10650 | 0.3468 | |
| | | 2.0789 | 10700 | 0.3448 | |
| | | 2.0886 | 10750 | 0.3524 | |
| | | 2.0983 | 10800 | 0.3691 | |
| | | 2.1080 | 10850 | 0.3505 | |
| | | 2.1177 | 10900 | 0.3253 | |
| | | 2.1275 | 10950 | 0.3422 | |
| | | 2.1372 | 11000 | 0.3321 | |
| | | 2.1469 | 11050 | 0.3392 | |
| | | 2.1566 | 11100 | 0.3292 | |
| | | 2.1663 | 11150 | 0.3572 | |
| | | 2.1760 | 11200 | 0.3483 | |
| | | 2.1857 | 11250 | 0.3535 | |
| | | 2.1955 | 11300 | 0.3559 | |
| | | 2.2052 | 11350 | 0.3331 | |
| | | 2.2149 | 11400 | 0.3367 | |
| | | 2.2246 | 11450 | 0.3538 | |
| | | 2.2343 | 11500 | 0.3458 | |
| | | 2.2440 | 11550 | 0.3197 | |
| | | 2.2537 | 11600 | 0.3587 | |
| | | 2.2635 | 11650 | 0.3565 | |
| | | 2.2732 | 11700 | 0.3533 | |
| | | 2.2829 | 11750 | 0.3191 | |
| | | 2.2926 | 11800 | 0.3591 | |
| | | 2.3023 | 11850 | 0.3598 | |
| | | 2.3120 | 11900 | 0.3495 | |
| | | 2.3217 | 11950 | 0.353 | |
| | | 2.3315 | 12000 | 0.3329 | |
| | | 2.3412 | 12050 | 0.3365 | |
| | | 2.3509 | 12100 | 0.3246 | |
| | | 2.3606 | 12150 | 0.3377 | |
| | | 2.3703 | 12200 | 0.3392 | |
| | | 2.3800 | 12250 | 0.3546 | |
| | | 2.3897 | 12300 | 0.3452 | |
| | | 2.3995 | 12350 | 0.3403 | |
| | | 2.4092 | 12400 | 0.3473 | |
| | | 2.4189 | 12450 | 0.336 | |
| | | 2.4286 | 12500 | 0.3591 | |
| | | 2.4383 | 12550 | 0.3425 | |
| | | 2.4480 | 12600 | 0.3293 | |
| | | 2.4577 | 12650 | 0.3339 | |
| | | 2.4675 | 12700 | 0.3386 | |
| | | 2.4772 | 12750 | 0.3335 | |
| | | 2.4869 | 12800 | 0.3249 | |
| | | 2.4966 | 12850 | 0.3123 | |
| | | 2.5063 | 12900 | 0.3182 | |
| | | 2.5160 | 12950 | 0.3282 | |
| | | 2.5257 | 13000 | 0.317 | |
| | | 2.5355 | 13050 | 0.3177 | |
| | | 2.5452 | 13100 | 0.3075 | |
| | | 2.5549 | 13150 | 0.3349 | |
| | | 2.5646 | 13200 | 0.3543 | |
| | | 2.5743 | 13250 | 0.3228 | |
| | | 2.5840 | 13300 | 0.3334 | |
| | | 2.5937 | 13350 | 0.3364 | |
| | | 2.6035 | 13400 | 0.333 | |
| | | 2.6132 | 13450 | 0.3633 | |
| | | 2.6229 | 13500 | 0.3547 | |
| | | 2.6326 | 13550 | 0.3431 | |
| | | 2.6423 | 13600 | 0.3265 | |
| | | 2.6520 | 13650 | 0.3197 | |
| | | 2.6617 | 13700 | 0.3233 | |
| | | 2.6715 | 13750 | 0.3293 | |
| | | 2.6812 | 13800 | 0.3249 | |
| | | 2.6909 | 13850 | 0.3041 | |
| | | 2.7006 | 13900 | 0.3612 | |
| | | 2.7103 | 13950 | 0.3391 | |
| | | 2.7200 | 14000 | 0.324 | |
| | | 2.7297 | 14050 | 0.3114 | |
| | | 2.7395 | 14100 | 0.3365 | |
| | | 2.7492 | 14150 | 0.2987 | |
| | | 2.7589 | 14200 | 0.3233 | |
| | | 2.7686 | 14250 | 0.3221 | |
| | | 2.7783 | 14300 | 0.3348 | |
| | | 2.7880 | 14350 | 0.3231 | |
| | | 2.7977 | 14400 | 0.3407 | |
| | | 2.8075 | 14450 | 0.3017 | |
| | | 2.8172 | 14500 | 0.3264 | |
| | | 2.8269 | 14550 | 0.3349 | |
| | | 2.8366 | 14600 | 0.3217 | |
| | | 2.8463 | 14650 | 0.2965 | |
| | | 2.8560 | 14700 | 0.322 | |
| | | 2.8657 | 14750 | 0.3195 | |
| | | 2.8755 | 14800 | 0.3021 | |
| | | 2.8852 | 14850 | 0.299 | |
| | | 2.8949 | 14900 | 0.1857 | |
| | | 2.9046 | 14950 | 0.1839 | |
| | | 2.9143 | 15000 | 0.1171 | |
| | | 2.9240 | 15050 | 0.1275 | |
| | | 2.9337 | 15100 | 0.1814 | |
| | | 2.9435 | 15150 | 0.1778 | |
| | | 2.9532 | 15200 | 0.142 | |
| | | 2.9629 | 15250 | 0.2545 | |
| | | 2.9726 | 15300 | 0.1202 | |
| | | 2.9823 | 15350 | 0.132 | |
| | | 2.9920 | 15400 | 0.154 | |
| | | 3.0017 | 15450 | 0.2622 | |
| | | 3.0115 | 15500 | 0.3185 | |
| | | 3.0212 | 15550 | 0.293 | |
| | | 3.0309 | 15600 | 0.3164 | |
| | | 3.0406 | 15650 | 0.2934 | |
| | | 3.0503 | 15700 | 0.3005 | |
| | | 3.0600 | 15750 | 0.3017 | |
| | | 3.0697 | 15800 | 0.2965 | |
| | | 3.0795 | 15850 | 0.309 | |
| | | 3.0892 | 15900 | 0.3056 | |
| | | 3.0989 | 15950 | 0.3318 | |
| | | 3.1086 | 16000 | 0.3094 | |
| | | 3.1183 | 16050 | 0.3041 | |
| | | 3.1280 | 16100 | 0.2981 | |
| | | 3.1378 | 16150 | 0.316 | |
| | | 3.1475 | 16200 | 0.3086 | |
| | | 3.1572 | 16250 | 0.3062 | |
| | | 3.1669 | 16300 | 0.3069 | |
| | | 3.1766 | 16350 | 0.312 | |
| | | 3.1863 | 16400 | 0.3161 | |
| | | 3.1960 | 16450 | 0.3059 | |
| | | 3.2058 | 16500 | 0.2899 | |
| | | 3.2155 | 16550 | 0.312 | |
| | | 3.2252 | 16600 | 0.3189 | |
| | | 3.2349 | 16650 | 0.3152 | |
| | | 3.2446 | 16700 | 0.2998 | |
| | | 3.2543 | 16750 | 0.301 | |
| | | 3.2640 | 16800 | 0.3129 | |
| | | 3.2738 | 16850 | 0.2955 | |
| | | 3.2835 | 16900 | 0.2923 | |
| | | 3.2932 | 16950 | 0.3111 | |
| | | 3.3029 | 17000 | 0.3097 | |
| | | 3.3126 | 17050 | 0.3045 | |
| | | 3.3223 | 17100 | 0.296 | |
| | | 3.3320 | 17150 | 0.3086 | |
| | | 3.3418 | 17200 | 0.2902 | |
| | | 3.3515 | 17250 | 0.322 | |
| | | 3.3612 | 17300 | 0.3105 | |
| | | 3.3709 | 17350 | 0.3048 | |
| | | 3.3806 | 17400 | 0.2853 | |
| | | 3.3903 | 17450 | 0.2795 | |
| | | 3.4000 | 17500 | 0.2933 | |
| | | 3.4098 | 17550 | 0.2834 | |
| | | 3.4195 | 17600 | 0.3 | |
| | | 3.4292 | 17650 | 0.2998 | |
| | | 3.4389 | 17700 | 0.2972 | |
| | | 3.4486 | 17750 | 0.285 | |
| | | 3.4583 | 17800 | 0.2888 | |
| | | 3.4680 | 17850 | 0.293 | |
| | | 3.4778 | 17900 | 0.2941 | |
| | | 3.4875 | 17950 | 0.3 | |
| | | 3.4972 | 18000 | 0.3022 | |
| | | 3.5069 | 18050 | 0.3049 | |
| | | 3.5166 | 18100 | 0.3067 | |
| | | 3.5263 | 18150 | 0.2934 | |
| | | 3.5360 | 18200 | 0.312 | |
| | | 3.5458 | 18250 | 0.2823 | |
| | | 3.5555 | 18300 | 0.2746 | |
| | | 3.5652 | 18350 | 0.2971 | |
| | | 3.5749 | 18400 | 0.2827 | |
| | | 3.5846 | 18450 | 0.2718 | |
| | | 3.5943 | 18500 | 0.2908 | |
| | | 3.6040 | 18550 | 0.2911 | |
| | | 3.6138 | 18600 | 0.3008 | |
| | | 3.6235 | 18650 | 0.3058 | |
| | | 3.6332 | 18700 | 0.304 | |
| | | 3.6429 | 18750 | 0.284 | |
| | | 3.6526 | 18800 | 0.3037 | |
| | | 3.6623 | 18850 | 0.2768 | |
| | | 3.6720 | 18900 | 0.3287 | |
| | | 3.6818 | 18950 | 0.2768 | |
| | | 3.6915 | 19000 | 0.316 | |
| | | 3.7012 | 19050 | 0.2786 | |
| | | 3.7109 | 19100 | 0.2746 | |
| | | 3.7206 | 19150 | 0.2794 | |
| | | 3.7303 | 19200 | 0.2869 | |
| | | 3.7400 | 19250 | 0.2836 | |
| | | 3.7498 | 19300 | 0.2982 | |
| | | 3.7595 | 19350 | 0.3143 | |
| | | 3.7692 | 19400 | 0.2942 | |
| | | 3.7789 | 19450 | 0.2693 | |
| | | 3.7886 | 19500 | 0.2894 | |
| | | 3.7983 | 19550 | 0.3009 | |
| | | 3.8080 | 19600 | 0.2893 | |
| | | 3.8178 | 19650 | 0.2915 | |
| | | 3.8275 | 19700 | 0.2991 | |
| | | 3.8372 | 19750 | 0.2857 | |
| | | 3.8469 | 19800 | 0.3028 | |
| | | 3.8566 | 19850 | 0.3068 | |
| | | 3.8663 | 19900 | 0.2955 | |
| | | 3.8760 | 19950 | 0.3119 | |
| | | 3.8858 | 20000 | 0.3364 | |
| | | 3.8955 | 20050 | 0.0993 | |
| | | 3.9052 | 20100 | 0.1208 | |
| | | 3.9149 | 20150 | 0.1015 | |
| | | 3.9246 | 20200 | 0.1422 | |
| | | 3.9343 | 20250 | 0.1879 | |
| | | 3.9440 | 20300 | 0.1437 | |
| | | 3.9538 | 20350 | 0.1556 | |
| | | 3.9635 | 20400 | 0.1279 | |
| | | 3.9732 | 20450 | 0.1384 | |
| | | 3.9829 | 20500 | 0.1556 | |
| | | 3.9926 | 20550 | 0.1508 | |
| | | 4.0023 | 20600 | 0.1812 | |
| | | 4.0120 | 20650 | 0.2858 | |
| | | 4.0218 | 20700 | 0.2807 | |
| | | 4.0315 | 20750 | 0.3016 | |
| | | 4.0412 | 20800 | 0.2611 | |
| | | 4.0509 | 20850 | 0.3031 | |
| | | 4.0606 | 20900 | 0.2772 | |
| | | 4.0703 | 20950 | 0.2776 | |
| | | 4.0800 | 21000 | 0.2556 | |
| | | 4.0898 | 21050 | 0.2744 | |
| | | 4.0995 | 21100 | 0.2825 | |
| | | 4.1092 | 21150 | 0.2664 | |
| | | 4.1189 | 21200 | 0.2772 | |
| | | 4.1286 | 21250 | 0.2767 | |
| | | 4.1383 | 21300 | 0.2562 | |
| | | 4.1480 | 21350 | 0.256 | |
| | | 4.1578 | 21400 | 0.2824 | |
| | | 4.1675 | 21450 | 0.2762 | |
| | | 4.1772 | 21500 | 0.2766 | |
| | | 4.1869 | 21550 | 0.291 | |
| | | 4.1966 | 21600 | 0.2636 | |
| | | 4.2063 | 21650 | 0.2751 | |
| | | 4.2160 | 21700 | 0.2739 | |
| | | 4.2258 | 21750 | 0.2982 | |
| | | 4.2355 | 21800 | 0.2881 | |
| | | 4.2452 | 21850 | 0.2687 | |
| | | 4.2549 | 21900 | 0.2644 | |
| | | 4.2646 | 21950 | 0.2827 | |
| | | 4.2743 | 22000 | 0.2591 | |
| | | 4.2840 | 22050 | 0.2645 | |
| | | 4.2938 | 22100 | 0.2786 | |
| | | 4.3035 | 22150 | 0.2693 | |
| | | 4.3132 | 22200 | 0.2909 | |
| | | 4.3229 | 22250 | 0.2838 | |
| | | 4.3326 | 22300 | 0.2901 | |
| | | 4.3423 | 22350 | 0.2629 | |
| | | 4.3520 | 22400 | 0.2672 | |
| | | 4.3618 | 22450 | 0.2962 | |
| | | 4.3715 | 22500 | 0.2742 | |
| | | 4.3812 | 22550 | 0.2811 | |
| | | 4.3909 | 22600 | 0.2639 | |
| | | 4.4006 | 22650 | 0.244 | |
| | | 4.4103 | 22700 | 0.2866 | |
| | | 4.4201 | 22750 | 0.2968 | |
| | | 4.4298 | 22800 | 0.2828 | |
| | | 4.4395 | 22850 | 0.2515 | |
| | | 4.4492 | 22900 | 0.282 | |
| | | 4.4589 | 22950 | 0.282 | |
| | | 4.4686 | 23000 | 0.2776 | |
| | | 4.4783 | 23050 | 0.2795 | |
| | | 4.4881 | 23100 | 0.2701 | |
| | | 4.4978 | 23150 | 0.2808 | |
| | | 4.5075 | 23200 | 0.2651 | |
| | | 4.5172 | 23250 | 0.2631 | |
| | | 4.5269 | 23300 | 0.2911 | |
| | | 4.5366 | 23350 | 0.2615 | |
| | | 4.5463 | 23400 | 0.2772 | |
| | | 4.5561 | 23450 | 0.2826 | |
| | | 4.5658 | 23500 | 0.2797 | |
| | | 4.5755 | 23550 | 0.2954 | |
| | | 4.5852 | 23600 | 0.2816 | |
| | | 4.5949 | 23650 | 0.2889 | |
| | | 4.6046 | 23700 | 0.2647 | |
| | | 4.6143 | 23750 | 0.2882 | |
| | | 4.6241 | 23800 | 0.2709 | |
| | | 4.6338 | 23850 | 0.2794 | |
| | | 4.6435 | 23900 | 0.2702 | |
| | | 4.6532 | 23950 | 0.2527 | |
| | | 4.6629 | 24000 | 0.2642 | |
| | | 4.6726 | 24050 | 0.2808 | |
| | | 4.6823 | 24100 | 0.2764 | |
| | | 4.6921 | 24150 | 0.2583 | |
| | | 4.7018 | 24200 | 0.2286 | |
| | | 4.7115 | 24250 | 0.2707 | |
| | | 4.7212 | 24300 | 0.2793 | |
| | | 4.7309 | 24350 | 0.2593 | |
| | | 4.7406 | 24400 | 0.2779 | |
| | | 4.7503 | 24450 | 0.3168 | |
| | | 4.7601 | 24500 | 0.2943 | |
| | | 4.7698 | 24550 | 0.3078 | |
| | | 4.7795 | 24600 | 0.2735 | |
| | | 4.7892 | 24650 | 0.2846 | |
| | | 4.7989 | 24700 | 0.2571 | |
| | | 4.8086 | 24750 | 0.2785 | |
| | | 4.8183 | 24800 | 0.2753 | |
| | | 4.8281 | 24850 | 0.2943 | |
| | | 4.8378 | 24900 | 0.264 | |
| | | 4.8475 | 24950 | 0.2962 | |
| | | 4.8572 | 25000 | 0.2743 | |
| | | 4.8669 | 25050 | 0.2748 | |
| | | 4.8766 | 25100 | 0.3039 | |
| | | 4.8863 | 25150 | 0.2817 | |
| | | 4.8961 | 25200 | 0.1467 | |
| | | 4.9058 | 25250 | 0.1224 | |
| | | 4.9155 | 25300 | 0.0547 | |
| | | 4.9252 | 25350 | 0.1329 | |
| | | 4.9349 | 25400 | 0.086 | |
| | | 4.9446 | 25450 | 0.1423 | |
| | | 4.9543 | 25500 | 0.0783 | |
| | | 4.9641 | 25550 | 0.1377 | |
| | | 4.9738 | 25600 | 0.0743 | |
| | | 4.9835 | 25650 | 0.0879 | |
| | | 4.9932 | 25700 | 0.1108 | |
| |
|
| | </details> |
| |
|
| | ### Framework Versions |
| | - Python: 3.11.13 |
| | - Sentence Transformers: 5.0.0 |
| | - Transformers: 4.56.2 |
| | - PyTorch: 2.6.0+cu124 |
| | - Accelerate: 1.8.1 |
| | - Datasets: 4.0.0 |
| | - Tokenizers: 0.22.1 |
| |
|
| | ## Citation |
| |
|
| | ### BibTeX |
| |
|
| | #### Sentence Transformers |
| | ```bibtex |
| | @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 |
| | ```bibtex |
| | @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} |
| | } |
| | ``` |
| |
|
| | <!-- |
| | ## Glossary |
| |
|
| | *Clearly define terms in order to be accessible across audiences.* |
| | --> |
| |
|
| | <!-- |
| | ## Model Card Authors |
| |
|
| | *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* |
| | --> |
| |
|
| | <!-- |
| | ## Model Card Contact |
| |
|
| | *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* |
| | --> |
