youssefkhalil320/mxbai-embed-large-v1-medical-nli_v1

SentenceTransformer based on mixedbread-ai/mxbai-embed-large-v1

This is a sentence-transformers model finetuned from mixedbread-ai/mxbai-embed-large-v1. It maps sentences & paragraphs to a 1024-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: mixedbread-ai/mxbai-embed-large-v1
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 1024 dimensions
• 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': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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("youssefkhalil320/mxbai-embed-large-v1-medical-nli_v1")
# Run inference
sentences = [
    "Given the patient's recent surgery and that the bleeding had stopped a colonoscopy was planned as an outpatient.",
    'Patient has significant PSH',
    'Patient has colon cancer',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

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

Evaluation

Metrics

Triplet

• Dataset: val-triplets
• Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.9062

Training Details

Training Dataset

Unnamed Dataset

• Size: 7,603 training samples
• Columns: anchor, positive, and negative
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative
  type	string	string	string
  details	min: 6 tokens mean: 29.42 tokens max: 256 tokens	min: 4 tokens mean: 9.38 tokens max: 25 tokens	min: 4 tokens mean: 8.89 tokens max: 21 tokens

• Samples:

  anchor	positive	negative
  O2: 94% 4Lnc.	The patient is on 4L of oxygen via nasal cannula	The patient’s oxygen saturation is 100% on room air
  The patient has received 500 mg of intravenously levofloxacin given at the outside hospital, and the patient has received intravenous vancomycin as well as ceftazidime in our Emergency Department.	The patient has received broad spectrum antibiotics.	The patient has pneumonia.
  Cardiac enzymes done at OSH showed CK 363, CK-MB 33, TropI 6.78.	The patient has cardiac ischemia.	The patient has normal cardiac perfusion.

• Loss: TripletLoss with these parameters:

  {
      "distance_metric": "TripletDistanceMetric.COSINE",
      "triplet_margin": 0.3
  }
  

Evaluation Dataset

Unnamed Dataset

• Size: 938 evaluation samples
• Columns: anchor, positive, and negative
• Approximate statistics based on the first 938 samples:

  	anchor	positive	negative
  type	string	string	string
  details	min: 6 tokens mean: 31.03 tokens max: 187 tokens	min: 4 tokens mean: 9.08 tokens max: 21 tokens	min: 4 tokens mean: 8.76 tokens max: 19 tokens

• Samples:

  anchor	positive	negative
  History of acute renal failure.	The patient has had kidney damage.	The patient has always had normal functioning kidneys.
  Of note, pt had recent workup for intermittent abd discomfort and bloating, CT abd showed cholelithiasis and endometrial thickening, due for endometrial biopsy with Gyn.	Patient has findings warranting biopsy on imaging	Patient has endometrial cancer
  She states she drinks about [2-17] glasses of wine per night, but also admits to drinking up to a full bottle of wine during the day when she is home alone.	the patient consumes alcohol	the patient denies alcohol use

• Loss: TripletLoss with these parameters:

  {
      "distance_metric": "TripletDistanceMetric.COSINE",
      "triplet_margin": 0.3
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 32
• learning_rate: 2e-05
• weight_decay: 0.01
• num_train_epochs: 40.0
• warmup_ratio: 0.1
• load_best_model_at_end: True
• push_to_hub: True
• hub_model_id: youssefkhalil320/mxbai-embed-large-v1-medical-nli_v1

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: 32
• 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: 0.01
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 40.0
• 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: 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: True
• resume_from_checkpoint: None
• hub_model_id: youssefkhalil320/mxbai-embed-large-v1-medical-nli_v1
• 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
• eval_use_gather_object: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss	Validation Loss	val-triplets_cosine_accuracy
0.1008	48	0.2288	-	-
0.2017	96	0.2112	-	-
0.3025	144	0.1781	-	-
0.4034	192	0.1514	-	-
0.5042	240	0.1345	-	-
0.6050	288	0.1284	-	-
0.7059	336	0.1182	-	-
0.8067	384	0.1099	-	-
0.9076	432	0.1148	-	-
1.0	476	-	0.0777	0.9264
1.0084	480	0.0884	-	-
1.1092	528	0.0809	-	-
1.2101	576	0.0766	-	-
1.3109	624	0.0752	-	-
1.4118	672	0.0696	-	-
1.5126	720	0.0716	-	-
1.6134	768	0.0761	-	-
1.7143	816	0.0677	-	-
1.8151	864	0.0718	-	-
1.9160	912	0.064	-	-
2.0	952	-	0.0649	0.9254
2.0168	960	0.0547	-	-
2.1176	1008	0.0422	-	-
2.2185	1056	0.0329	-	-
2.3193	1104	0.0461	-	-
2.4202	1152	0.0389	-	-
2.5210	1200	0.0412	-	-
2.6218	1248	0.0422	-	-
2.7227	1296	0.0435	-	-
2.8235	1344	0.0496	-	-
2.9244	1392	0.04	-	-
3.0	1428	-	0.0676	0.9104
3.0252	1440	0.0324	-	-
3.1261	1488	0.0197	-	-
3.2269	1536	0.0176	-	-
3.3277	1584	0.0197	-	-
3.4286	1632	0.025	-	-
3.5294	1680	0.0286	-	-
3.6303	1728	0.0245	-	-
3.7311	1776	0.0228	-	-
3.8319	1824	0.0269	-	-
3.9328	1872	0.029	-	-
4.0	1904	-	0.0704	0.9179
4.0336	1920	0.0213	-	-
4.1345	1968	0.0133	-	-
4.2353	2016	0.0123	-	-
4.3361	2064	0.0142	-	-
4.4370	2112	0.0168	-	-
4.5378	2160	0.0149	-	-
4.6387	2208	0.0126	-	-
4.7395	2256	0.013	-	-
4.8403	2304	0.0134	-	-
4.9412	2352	0.0196	-	-
5.0	2380	-	0.0602	0.9222
5.0420	2400	0.0123	-	-
5.1429	2448	0.0094	-	-
5.2437	2496	0.0081	-	-
5.3445	2544	0.0093	-	-
5.4454	2592	0.0095	-	-
5.5462	2640	0.0085	-	-
5.6471	2688	0.0082	-	-
5.7479	2736	0.0107	-	-
5.8487	2784	0.0065	-	-
5.9496	2832	0.0092	-	-
6.0	2856	-	0.0629	0.9158
6.0504	2880	0.0043	-	-
6.1513	2928	0.0053	-	-
6.2521	2976	0.0071	-	-
6.3529	3024	0.0066	-	-
6.4538	3072	0.0041	-	-
6.5546	3120	0.0039	-	-
6.6555	3168	0.006	-	-
6.7563	3216	0.0072	-	-
6.8571	3264	0.0054	-	-
6.9580	3312	0.0055	-	-
7.0	3332	-	0.0692	0.9115
7.0588	3360	0.0078	-	-
7.1597	3408	0.0024	-	-
7.2605	3456	0.0016	-	-
7.3613	3504	0.0039	-	-
7.4622	3552	0.0048	-	-
7.5630	3600	0.0034	-	-
7.6639	3648	0.0034	-	-
7.7647	3696	0.0031	-	-
7.8655	3744	0.0045	-	-
7.9664	3792	0.0058	-	-
8.0	3808	-	0.0663	0.9126
8.0672	3840	0.0038	-	-
8.1681	3888	0.003	-	-
8.2689	3936	0.0028	-	-
8.3697	3984	0.0043	-	-
8.4706	4032	0.0032	-	-
8.5714	4080	0.0038	-	-
8.6723	4128	0.0018	-	-
8.7731	4176	0.0044	-	-
8.8739	4224	0.0037	-	-
8.9748	4272	0.003	-	-
9.0	4284	-	0.0597	0.9232
9.0756	4320	0.0018	-	-
9.1765	4368	0.0016	-	-
9.2773	4416	0.0011	-	-
9.3782	4464	0.0027	-	-
9.4790	4512	0.0035	-	-
9.5798	4560	0.0031	-	-
9.6807	4608	0.0023	-	-
9.7815	4656	0.0024	-	-
9.8824	4704	0.0021	-	-
9.9832	4752	0.0036	-	-
10.0	4760	-	0.0618	0.9190
10.0840	4800	0.0016	-	-
10.1849	4848	0.003	-	-
10.2857	4896	0.0017	-	-
10.3866	4944	0.002	-	-
10.4874	4992	0.002	-	-
10.5882	5040	0.0031	-	-
10.6891	5088	0.0022	-	-
10.7899	5136	0.0019	-	-
10.8908	5184	0.0013	-	-
10.9916	5232	0.0037	-	-
11.0	5236	-	0.0647	0.9147
11.0924	5280	0.003	-	-
11.1933	5328	0.0007	-	-
11.2941	5376	0.002	-	-
11.3950	5424	0.0026	-	-
11.4958	5472	0.0019	-	-
11.5966	5520	0.0017	-	-
11.6975	5568	0.0017	-	-
11.7983	5616	0.003	-	-
11.8992	5664	0.0053	-	-
12.0	5712	0.0028	0.0634	0.9168
12.1008	5760	0.0015	-	-
12.2017	5808	0.002	-	-
12.3025	5856	0.0013	-	-
12.4034	5904	0.002	-	-
12.5042	5952	0.0019	-	-
12.6050	6000	0.0017	-	-
12.7059	6048	0.0011	-	-
12.8067	6096	0.001	-	-
12.9076	6144	0.0016	-	-
13.0	6188	-	0.0619	0.9243
13.0084	6192	0.0023	-	-
13.1092	6240	0.0018	-	-
13.2101	6288	0.0014	-	-
13.3109	6336	0.0008	-	-
13.4118	6384	0.0017	-	-
13.5126	6432	0.0003	-	-
13.6134	6480	0.0014	-	-
13.7143	6528	0.0002	-	-
13.8151	6576	0.0011	-	-
13.9160	6624	0.0013	-	-
14.0	6664	-	0.0659	0.9083
14.0168	6672	0.0021	-	-
14.1176	6720	0.0016	-	-
14.2185	6768	0.0014	-	-
14.3193	6816	0.0009	-	-
14.4202	6864	0.0014	-	-
14.5210	6912	0.0016	-	-
14.6218	6960	0.0015	-	-
14.7227	7008	0.0011	-	-
14.8235	7056	0.0016	-	-
14.9244	7104	0.0017	-	-
15.0	7140	-	0.0641	0.9147
15.0252	7152	0.0004	-	-
15.1261	7200	0.0004	-	-
15.2269	7248	0.0007	-	-
15.3277	7296	0.0016	-	-
15.4286	7344	0.0013	-	-
15.5294	7392	0.0011	-	-
15.6303	7440	0.0012	-	-
15.7311	7488	0.0032	-	-
15.8319	7536	0.0011	-	-
15.9328	7584	0.0019	-	-
16.0	7616	-	0.0668	0.9072
16.0336	7632	0.0023	-	-
16.1345	7680	0.0012	-	-
16.2353	7728	0.0015	-	-
16.3361	7776	0.0007	-	-
16.4370	7824	0.0018	-	-
16.5378	7872	0.0015	-	-
16.6387	7920	0.0011	-	-
16.7395	7968	0.0019	-	-
16.8403	8016	0.0025	-	-
16.9412	8064	0.0011	-	-
17.0	8092	-	0.0649	0.9190
17.0420	8112	0.0022	-	-
17.1429	8160	0.0012	-	-
17.2437	8208	0.0002	-	-
17.3445	8256	0.0014	-	-
17.4454	8304	0.0011	-	-
17.5462	8352	0.0013	-	-
17.6471	8400	0.0013	-	-
17.7479	8448	0.001	-	-
17.8487	8496	0.0003	-	-
17.9496	8544	0.0008	-	-
18.0	8568	-	0.0656	0.9083
18.0504	8592	0.0007	-	-
18.1513	8640	0.0009	-	-
18.2521	8688	0.0008	-	-
18.3529	8736	0.0004	-	-
18.4538	8784	0.0009	-	-
18.5546	8832	0.0007	-	-
18.6555	8880	0.002	-	-
18.7563	8928	0.0011	-	-
18.8571	8976	0.0005	-	-
18.9580	9024	0.0012	-	-
19.0	9044	-	0.0693	0.9136
19.0588	9072	0.0012	-	-
19.1597	9120	0.0003	-	-
19.2605	9168	0.0015	-	-
19.3613	9216	0.0014	-	-
19.4622	9264	0.0005	-	-
19.5630	9312	0.0012	-	-
19.6639	9360	0.0008	-	-
19.7647	9408	0.0017	-	-
19.8655	9456	0.001	-	-
19.9664	9504	0.0018	-	-
20.0	9520	-	0.0697	0.9094
20.0672	9552	0.0002	-	-
20.1681	9600	0.0003	-	-
20.2689	9648	0.0022	-	-
20.3697	9696	0.001	-	-
20.4706	9744	0.0014	-	-
20.5714	9792	0.0007	-	-
20.6723	9840	0.0006	-	-
20.7731	9888	0.001	-	-
20.8739	9936	0.0004	-	-
20.9748	9984	0.0011	-	-
21.0	9996	-	0.0696	0.9083
21.0756	10032	0.0005	-	-
21.1765	10080	0.0003	-	-
21.2773	10128	0.0005	-	-
21.3782	10176	0.0013	-	-
21.4790	10224	0.0009	-	-
21.5798	10272	0.0016	-	-
21.6807	10320	0.0012	-	-
21.7815	10368	0.0009	-	-
21.8824	10416	0.001	-	-
21.9832	10464	0.0013	-	-
22.0	10472	-	0.0676	0.9136
22.0840	10512	0.0017	-	-
22.1849	10560	0.0001	-	-
22.2857	10608	0.0009	-	-
22.3866	10656	0.0003	-	-
22.4874	10704	0.0013	-	-
22.5882	10752	0.0002	-	-
22.6891	10800	0.0014	-	-
22.7899	10848	0.001	-	-
22.8908	10896	0.0004	-	-
22.9916	10944	0.0008	-	-
23.0	10948	-	0.0672	0.9094
23.0924	10992	0.0004	-	-
23.1933	11040	0.0005	-	-
23.2941	11088	0.0004	-	-
23.3950	11136	0.0008	-	-
23.4958	11184	0.001	-	-
23.5966	11232	0.0001	-	-
23.6975	11280	0.0007	-	-
23.7983	11328	0.0004	-	-
23.8992	11376	0.0006	-	-
24.0	11424	0.0007	0.0634	0.9158
24.1008	11472	0.0002	-	-
24.2017	11520	0.0003	-	-
24.3025	11568	0.0006	-	-
24.4034	11616	0.0008	-	-
24.5042	11664	0.001	-	-
24.6050	11712	0.0001	-	-
24.7059	11760	0.0003	-	-
24.8067	11808	0.0001	-	-
24.9076	11856	0.0006	-	-
25.0	11900	-	0.0636	0.9200
25.0084	11904	0.0003	-	-
25.1092	11952	0.0004	-	-
25.2101	12000	0.0007	-	-
25.3109	12048	0.0004	-	-
25.4118	12096	0.0002	-	-
25.5126	12144	0.0002	-	-
25.6134	12192	0.0005	-	-
25.7143	12240	0.0008	-	-
25.8151	12288	0.0009	-	-
25.9160	12336	0.0002	-	-
26.0	12376	-	0.0669	0.9104
26.0168	12384	0.0005	-	-
26.1176	12432	0.0002	-	-
26.2185	12480	0.0004	-	-
26.3193	12528	0.0003	-	-
26.4202	12576	0.0002	-	-
26.5210	12624	0.0006	-	-
26.6218	12672	0.0	-	-
26.7227	12720	0.001	-	-
26.8235	12768	0.0003	-	-
26.9244	12816	0.0006	-	-
27.0	12852	-	0.0653	0.9072
27.0252	12864	0.0004	-	-
27.1261	12912	0.0005	-	-
27.2269	12960	0.0005	-	-
27.3277	13008	0.0007	-	-
27.4286	13056	0.0002	-	-
27.5294	13104	0.0005	-	-
27.6303	13152	0.0002	-	-
27.7311	13200	0.0005	-	-
27.8319	13248	0.0009	-	-
27.9328	13296	0.0002	-	-
28.0	13328	-	0.0627	0.9158
28.0336	13344	0.0007	-	-
28.1345	13392	0.0002	-	-
28.2353	13440	0.0	-	-
28.3361	13488	0.0004	-	-
28.4370	13536	0.0011	-	-
28.5378	13584	0.0002	-	-
28.6387	13632	0.0006	-	-
28.7395	13680	0.0003	-	-
28.8403	13728	0.0006	-	-
28.9412	13776	0.0005	-	-
29.0	13804	-	0.0682	0.9072
29.0420	13824	0.0003	-	-
29.1429	13872	0.0002	-	-
29.2437	13920	0.0	-	-
29.3445	13968	0.0001	-	-
29.4454	14016	0.0001	-	-
29.5462	14064	0.0	-	-
29.6471	14112	0.0006	-	-
29.7479	14160	0.0008	-	-
29.8487	14208	0.0008	-	-
29.9496	14256	0.0006	-	-
30.0	14280	-	0.0681	0.9104
30.0504	14304	0.0	-	-
30.1513	14352	0.0003	-	-
30.2521	14400	0.0002	-	-
30.3529	14448	0.0002	-	-
30.4538	14496	0.0001	-	-
30.5546	14544	0.0001	-	-
30.6555	14592	0.0005	-	-
30.7563	14640	0.0007	-	-
30.8571	14688	0.0001	-	-
30.9580	14736	0.0004	-	-
31.0	14756	-	0.0645	0.9094
31.0588	14784	0.0	-	-
31.1597	14832	0.0	-	-
31.2605	14880	0.0001	-	-
31.3613	14928	0.0006	-	-
31.4622	14976	0.0	-	-
31.5630	15024	0.0	-	-
31.6639	15072	0.0007	-	-
31.7647	15120	0.0001	-	-
31.8655	15168	0.0005	-	-
31.9664	15216	0.0004	-	-
32.0	15232	-	0.0650	0.9072
32.0672	15264	0.0	-	-
32.1681	15312	0.0	-	-
32.2689	15360	0.0001	-	-
32.3697	15408	0.0005	-	-
32.4706	15456	0.0003	-	-
32.5714	15504	0.0	-	-
32.6723	15552	0.0001	-	-
32.7731	15600	0.001	-	-
32.8739	15648	0.0002	-	-
32.9748	15696	0.0001	-	-
33.0	15708	-	0.0670	0.9083
33.0756	15744	0.0	-	-
33.1765	15792	0.0	-	-
33.2773	15840	0.0001	-	-
33.3782	15888	0.0001	-	-
33.4790	15936	0.0003	-	-
33.5798	15984	0.0007	-	-
33.6807	16032	0.0001	-	-
33.7815	16080	0.0002	-	-
33.8824	16128	0.0	-	-
33.9832	16176	0.0004	-	-
34.0	16184	-	0.0655	0.9062
34.0840	16224	0.0003	-	-
34.1849	16272	0.0004	-	-
34.2857	16320	0.0001	-	-
34.3866	16368	0.0007	-	-
34.4874	16416	0.0	-	-
34.5882	16464	0.0	-	-
34.6891	16512	0.0004	-	-
34.7899	16560	0.0	-	-
34.8908	16608	0.0003	-	-
34.9916	16656	0.0	-	-
35.0	16660	-	0.0667	0.9062
35.0924	16704	0.0	-	-
35.1933	16752	0.0001	-	-
35.2941	16800	0.0	-	-
35.3950	16848	0.0	-	-
35.4958	16896	0.0001	-	-
35.5966	16944	0.0004	-	-
35.6975	16992	0.0004	-	-
35.7983	17040	0.0003	-	-
35.8992	17088	0.0004	-	-
36.0	17136	0.0003	0.0658	0.9051
36.1008	17184	0.001	-	-
36.2017	17232	0.0	-	-
36.3025	17280	0.0	-	-
36.4034	17328	0.0	-	-
36.5042	17376	0.0003	-	-
36.6050	17424	0.0	-	-
36.7059	17472	0.0	-	-
36.8067	17520	0.0003	-	-
36.9076	17568	0.0002	-	-
37.0	17612	-	0.0662	0.9030
37.0084	17616	0.0004	-	-
37.1092	17664	0.0	-	-
37.2101	17712	0.0	-	-
37.3109	17760	0.0	-	-
37.4118	17808	0.0007	-	-
37.5126	17856	0.0	-	-
37.6134	17904	0.0001	-	-
37.7143	17952	0.0	-	-
37.8151	18000	0.0	-	-
37.9160	18048	0.0003	-	-
38.0	18088	-	0.0660	0.9062
38.0168	18096	0.0	-	-
38.1176	18144	0.0004	-	-
38.2185	18192	0.0	-	-
38.3193	18240	0.0	-	-
38.4202	18288	0.0	-	-
38.5210	18336	0.0007	-	-
38.6218	18384	0.0	-	-
38.7227	18432	0.0	-	-
38.8235	18480	0.0004	-	-
38.9244	18528	0.0	-	-
39.0	18564	-	0.0649	0.9072
39.0252	18576	0.0009	-	-
39.1261	18624	0.0004	-	-
39.2269	18672	0.0	-	-
39.3277	18720	0.0	-	-
39.4286	18768	0.0	-	-
39.5294	18816	0.0	-	-
39.6303	18864	0.0	-	-
39.7311	18912	0.0004	-	-
39.8319	18960	0.0	-	-
39.9328	19008	0.0006	-	-
40.0	19040	-	0.0647	0.9062

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.19
• Sentence Transformers: 3.3.1
• Transformers: 4.44.2
• PyTorch: 2.8.0+cu128
• Accelerate: 1.12.0
• Datasets: 4.0.0
• 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",
}

TripletLoss

@misc{hermans2017defense,
    title={In Defense of the Triplet Loss for Person Re-Identification},
    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
    year={2017},
    eprint={1703.07737},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}