along26/all-MiniLM-L6-v2_multilingual_malaysian-v5

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. 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: sentence-transformers/all-MiniLM-L6-v2
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 384 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': 512, 'do_lower_case': False, 'architecture': '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})
)

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("along26/all-MiniLM-L6-v2_multilingual_malaysian-v5")
# Run inference
sentences = [
    'How can we design small molecule inhibitors of viral protein targets to prevent the replication of the influenza virus?',
    'Bagaimanakah kita boleh mereka bentuk perencat molekul kecil sasaran protein virus untuk mencegah replikasi virus influenza?',
    "How does the Malaysian government's authoritarian approach to dissent and free speech stifle progressive movements and limit the potential for democratic reform?",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000, -0.0699,  0.9941],
#         [-0.0699,  1.0000, -0.0800],
#         [ 0.9941, -0.0800,  1.0000]])

Evaluation

Metrics

Triplet

• Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.0002

Training Details

Training Dataset

Unnamed Dataset

• Size: 415,570 training samples
• Columns: anchor, positive, and negative
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative
  type	string	string	string
  details	min: 15 tokens mean: 230.67 tokens max: 512 tokens	min: 19 tokens mean: 273.54 tokens max: 512 tokens	min: 14 tokens mean: 239.81 tokens max: 512 tokens

• Samples:

  anchor	positive	negative
  How has the culture of corruption and cronyism under Najib Razak's administration affected the Malaysian economy and social fabric?	Bagaimanakah budaya rasuah dan kronisme di bawah pentadbiran Najib Razak menjejaskan ekonomi dan fabrik sosial Malaysia?	What is the role of the pancreas in the human digestive system and how does its anatomy support this function?
  Why have some opposition politicians in Malaysia criticized the government's handling of the 1MDB scandal and called for more transparency?	Mengapa beberapa ahli politik pembangkang di Malaysia mengkritik pengendalian kerajaan terhadap skandal 1MDB dan meminta lebih ketelusan?	The formation of heavy elements (nucleosynthesis) inside a star involves several processes, which are affected by the star's evolution. These processes include: 1. Hydrogen burning (nuclear fusion): This is the initial stage of a star's life, where hydrogen nuclei (protons) combine to form helium nuclei (alpha particles) through a series of reactions called the proton-proton chain or the CNO cycle (carbon-nitrogen-oxygen). This process releases a large amount of energy in the form of light and heat, which causes the star to shine. 2. Helium burning (triple-alpha process): As the hydrogen in the core of the star is depleted, the core contracts and heats up, initiating the fusion of helium nuclei into heavier elements like carbon and oxygen. This process involves the combination of three helium nuclei (alpha particles) to form a carbon nucleus. 3. Carbon burning: In more massive stars, the core temperature increases further, allowing carbon nuclei to fuse with helium nuclei to form ox...
  How has Najib Razak's corruption allegedly contributed to social inequality and poverty in Malaysia?	Bagaimanakah rasuah Najib Razak didakwa menyumbang kepada ketidaksamaan sosial dan kemiskinan di Malaysia?	To estimate the age of a supermassive black hole with a mass of 1 billion solar masses, we can assume that it formed shortly after the Big Bang. The age of the universe is approximately 13.8 billion years old, so the black hole's age would be close to this value. Now, let's discuss the theoretical process for the formation and evolution of supermassive black holes in the early universe based on current astrophysical models. 1. Direct collapse: In the early universe, some regions with high-density gas could have collapsed directly into black holes without forming stars first. These black holes, called "seed" black holes, could then grow by accreting mass from their surroundings. This process is more efficient in the early universe due to the higher density of gas and the absence of supernova explosions, which can disperse gas and hinder black hole growth. 2. Stellar remnants: Massive stars in the early universe could have collapsed into black holes after their lifetimes. These black ...

• Loss: TripletLoss with these parameters:

  {
      "distance_metric": "TripletDistanceMetric.EUCLIDEAN",
      "triplet_margin": 5
  }
  

Evaluation Dataset

Unnamed Dataset

• Size: 5,000 evaluation samples
• Columns: anchor, positive, and negative
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative
  type	string	string	string
  details	min: 12 tokens mean: 219.95 tokens max: 512 tokens	min: 17 tokens mean: 263.51 tokens max: 512 tokens	min: 15 tokens mean: 236.31 tokens max: 512 tokens

• Samples:

  anchor	positive	negative
  Consider a graph with 8 vertices and 12 edges. Determine if the graph contains a perfect matching. If it does, provide one example of a perfect matching. If it does not, explain why a perfect matching is not possible.	Pertimbangkan graf dengan 8 bucu dan 12 tepi. Tentukan sama ada graf mengandungi padanan sempurna. Jika ya, berikan satu contoh padanan yang sempurna. Jika tidak, jelaskan mengapa padanan yang sempurna tidak dapat dilakukan.	The 1MDB scandal and the corruption charges against former Malaysian Prime Minister Najib Razak offer several important lessons for Malaysia and other countries: 1. Stronger checks and balances: The 1MDB scandal highlighted the need for stronger checks and balances in government agencies and institutions. Malaysia should consider implementing additional measures to prevent the misuse of power and public funds, including more robust auditing and oversight mechanisms, as well as stronger whistleblower protections. 2. Transparency and accountability: The lack of transparency and accountability surrounding 1MDB contributed to the scandal. Malaysia should prioritize transparency in government operations, including procurement processes and financial transactions. Implementing measures such as open data initiatives and requiring greater disclosure from government-linked companies could help promote accountability and reduce opportunities for corruption. 3. Strengthening law enforcement: The...
  What is the probability of flipping a fair coin three times and getting exactly two heads in a row?	Apakah kebarangkalian membalikkan syiling saksama tiga kali dan mendapat tepat dua kepala berturut-turut?	Why is corruption so rampant in Malaysia, with politicians and government officials often caught engaging in unethical practices?
  Why have there been allegations of corruption and mismanagement in Malaysia's state-owned enterprises, and what measures have been taken to address these issues?	Mengapa terdapat tuduhan rasuah dan salah urus dalam perusahaan milik kerajaan Malaysia, dan apakah langkah-langkah yang telah diambil untuk menangani isu-isu ini?	What is the pKa value of acetic acid, and how does it affect its acid strength when compared to other organic acids such as citric acid or benzoic acid? Provide an explanation for your answer using acid-base reaction principles in organic chemistry.

• Loss: TripletLoss with these parameters:

  {
      "distance_metric": "TripletDistanceMetric.EUCLIDEAN",
      "triplet_margin": 5
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• learning_rate: 1e-05
• weight_decay: 0.01
• warmup_steps: 100
• fp16: True
• load_best_model_at_end: 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: 32
• 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: 1e-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: 3
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• warmup_steps: 100
• 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
• 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: 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}
• parallelism_config: None
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch_fused
• optim_args: None
• adafactor: False
• group_by_length: False
• length_column_name: length
• project: huggingface
• trackio_space_id: trackio
• 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: no
• 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: True
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Click to expand

Epoch	Step	Training Loss	Validation Loss	cosine_accuracy
0.0077	100	4.1768	-	-
0.0154	200	1.8189	-	-
0.0231	300	1.4626	-	-
0.0308	400	1.4251	-	-
0.0385	500	1.3937	-	-
0.0462	600	1.3423	-	-
0.0539	700	1.2926	-	-
0.0616	800	1.38	-	-
0.0693	900	1.3513	-	-
0.0770	1000	1.3462	-	-
0.0847	1100	1.3262	-	-
0.0924	1200	1.2772	-	-
0.1001	1300	1.3334	-	-
0.1078	1400	1.3266	-	-
0.1155	1500	1.3311	-	-
0.1232	1600	1.3036	-	-
0.1309	1700	1.2544	-	-
0.1386	1800	1.317	-	-
0.1463	1900	1.2847	-	-
0.1540	2000	1.3146	-	-
0.1617	2100	1.3158	-	-
0.1694	2200	1.2892	-	-
0.1771	2300	1.274	-	-
0.1848	2400	1.2369	-	-
0.1925	2500	1.2799	-	-
0.2002	2600	1.3205	-	-
0.2079	2700	1.1933	-	-
0.2156	2800	1.2345	-	-
0.2233	2900	1.2547	-	-
0.2310	3000	1.2184	-	-
0.2387	3100	1.2213	-	-
0.2464	3200	1.2134	-	-
0.2541	3300	1.1824	-	-
0.2618	3400	1.2635	-	-
0.2695	3500	1.258	-	-
0.2772	3600	1.2524	-	-
0.2849	3700	1.2337	-	-
0.2926	3800	1.2788	-	-
0.3003	3900	1.2361	-	-
0.3080	4000	1.1743	-	-
0.3157	4100	1.1463	-	-
0.3234	4200	1.2053	-	-
0.3311	4300	1.2701	-	-
0.3388	4400	1.2369	-	-
0.3465	4500	1.2314	-	-
0.3542	4600	1.2543	-	-
0.3619	4700	1.2163	-	-
0.3696	4800	1.1994	-	-
0.3773	4900	1.1905	-	-
0.3850	5000	1.2708	0.0015	0.0092
0.3927	5100	1.1595	-	-
0.4004	5200	1.143	-	-
0.4081	5300	1.151	-	-
0.4158	5400	1.0917	-	-
0.4235	5500	1.1954	-	-
0.4312	5600	1.177	-	-
0.4389	5700	1.1427	-	-
0.4466	5800	1.158	-	-
0.4543	5900	1.2043	-	-
0.4620	6000	1.1107	-	-
0.4697	6100	1.1773	-	-
0.4774	6200	1.2008	-	-
0.4851	6300	1.1303	-	-
0.4928	6400	1.1576	-	-
0.5005	6500	1.2443	-	-
0.5082	6600	1.1195	-	-
0.5159	6700	1.1735	-	-
0.5236	6800	1.1326	-	-
0.5313	6900	1.1577	-	-
0.5390	7000	1.1121	-	-
0.5467	7100	1.0797	-	-
0.5544	7200	1.1129	-	-
0.5621	7300	1.1144	-	-
0.5698	7400	1.1844	-	-
0.5775	7500	1.0852	-	-
0.5852	7600	1.1529	-	-
0.5929	7700	1.1619	-	-
0.6006	7800	1.1049	-	-
0.6083	7900	1.0314	-	-
0.6160	8000	1.1343	-	-
0.6237	8100	1.1337	-	-
0.6314	8200	1.1416	-	-
0.6391	8300	1.1127	-	-
0.6468	8400	1.0403	-	-
0.6545	8500	1.1776	-	-
0.6622	8600	1.124	-	-
0.6699	8700	1.1172	-	-
0.6776	8800	1.1473	-	-
0.6853	8900	1.0843	-	-
0.6930	9000	1.1385	-	-
0.7007	9100	1.1291	-	-
0.7084	9200	1.0949	-	-
0.7161	9300	1.1137	-	-
0.7238	9400	1.0685	-	-
0.7315	9500	1.0659	-	-
0.7392	9600	1.1199	-	-
0.7469	9700	1.1223	-	-
0.7546	9800	1.1241	-	-
0.7623	9900	0.9998	-	-
0.7700	10000	1.0645	0.0008	0.0012
0.7777	10100	1.0987	-	-
0.7854	10200	1.126	-	-
0.7931	10300	1.1193	-	-
0.8008	10400	1.1361	-	-
0.8085	10500	1.0743	-	-
0.8162	10600	1.113	-	-
0.8239	10700	1.1109	-	-
0.8316	10800	1.1083	-	-
0.8393	10900	1.099	-	-
0.8470	11000	1.0308	-	-
0.8547	11100	1.0867	-	-
0.8624	11200	1.0447	-	-
0.8701	11300	1.1661	-	-
0.8778	11400	1.0973	-	-
0.8855	11500	1.0583	-	-
0.8932	11600	1.0728	-	-
0.9009	11700	1.0377	-	-
0.9086	11800	1.0505	-	-
0.9163	11900	1.0799	-	-
0.9240	12000	1.0908	-	-
0.9317	12100	1.0777	-	-
0.9394	12200	1.068	-	-
0.9471	12300	1.0695	-	-
0.9548	12400	1.0692	-	-
0.9625	12500	1.0522	-	-
0.9702	12600	0.968	-	-
0.9779	12700	1.0422	-	-
0.9856	12800	1.0816	-	-
0.9933	12900	1.0984	-	-
1.0010	13000	1.0601	-	-
1.0087	13100	0.995	-	-
1.0164	13200	1.0454	-	-
1.0241	13300	1.0421	-	-
1.0318	13400	1.0838	-	-
1.0395	13500	1.0858	-	-
1.0472	13600	1.0091	-	-
1.0549	13700	1.0391	-	-
1.0626	13800	1.0019	-	-
1.0703	13900	1.0824	-	-
1.0780	14000	1.0571	-	-
1.0857	14100	0.9976	-	-
1.0934	14200	1.0757	-	-
1.1011	14300	1.0679	-	-
1.1088	14400	1.049	-	-
1.1165	14500	0.9863	-	-
1.1242	14600	1.011	-	-
1.1319	14700	1.0596	-	-
1.1396	14800	1.0324	-	-
1.1473	14900	1.0592	-	-
1.1550	15000	1.0346	0.0008	0.0008
1.1627	15100	0.945	-	-
1.1704	15200	0.9627	-	-
1.1781	15300	1.0519	-	-
1.1858	15400	1.0867	-	-
1.1935	15500	0.9869	-	-
1.2012	15600	1.0141	-	-
1.2089	15700	1.007	-	-
1.2166	15800	1.0021	-	-
1.2243	15900	1.0186	-	-
1.2320	16000	1.0519	-	-
1.2397	16100	1.0673	-	-
1.2474	16200	0.9647	-	-
1.2551	16300	1.0051	-	-
1.2628	16400	0.9842	-	-
1.2705	16500	1.0234	-	-
1.2782	16600	1.0402	-	-
1.2859	16700	1.0481	-	-
1.2936	16800	0.9806	-	-
1.3013	16900	1.0481	-	-
1.3090	17000	0.9768	-	-
1.3167	17100	1.0416	-	-
1.3244	17200	0.962	-	-
1.3321	17300	0.9924	-	-
1.3398	17400	1.0057	-	-
1.3475	17500	1.0121	-	-
1.3552	17600	0.9902	-	-
1.3629	17700	0.9974	-	-
1.3706	17800	0.9696	-	-
1.3783	17900	1.011	-	-
1.3860	18000	0.9568	-	-
1.3937	18100	0.954	-	-
1.4014	18200	1.064	-	-
1.4091	18300	0.9787	-	-
1.4168	18400	1.0156	-	-
1.4245	18500	1.0027	-	-
1.4322	18600	0.9822	-	-
1.4399	18700	0.9801	-	-
1.4476	18800	1.0135	-	-
1.4553	18900	1.0043	-	-
1.4630	19000	0.9922	-	-
1.4707	19100	1.007	-	-
1.4784	19200	1.0055	-	-
1.4861	19300	0.9213	-	-
1.4938	19400	1.0014	-	-
1.5015	19500	0.9913	-	-
1.5092	19600	0.9461	-	-
1.5169	19700	0.9533	-	-
1.5246	19800	1.0001	-	-
1.5323	19900	0.9848	-	-
1.5400	20000	1.0388	0.0007	0.0006
1.5477	20100	0.9917	-	-
1.5554	20200	1.0273	-	-
1.5631	20300	0.9737	-	-
1.5708	20400	0.9747	-	-
1.5785	20500	0.9554	-	-
1.5862	20600	0.999	-	-
1.5939	20700	1.0367	-	-
1.6016	20800	0.9435	-	-
1.6093	20900	0.9849	-	-
1.6170	21000	0.97	-	-
1.6247	21100	0.9698	-	-
1.6324	21200	0.9321	-	-
1.6401	21300	0.9383	-	-
1.6478	21400	0.9258	-	-
1.6555	21500	0.9788	-	-
1.6632	21600	0.9313	-	-
1.6709	21700	1.0025	-	-
1.6786	21800	0.963	-	-
1.6863	21900	1.001	-	-
1.6940	22000	0.9945	-	-
1.7017	22100	0.9515	-	-
1.7094	22200	0.9673	-	-
1.7171	22300	0.992	-	-
1.7248	22400	0.9641	-	-
1.7325	22500	1.0091	-	-
1.7402	22600	1.0023	-	-
1.7479	22700	0.9313	-	-
1.7556	22800	1.0449	-	-
1.7633	22900	1.0116	-	-
1.7710	23000	0.9924	-	-
1.7787	23100	0.9076	-	-
1.7864	23200	0.9274	-	-
1.7941	23300	0.9759	-	-
1.8018	23400	0.9368	-	-
1.8095	23500	0.923	-	-
1.8172	23600	0.9868	-	-
1.8249	23700	0.959	-	-
1.8326	23800	0.9486	-	-
1.8403	23900	0.9812	-	-
1.8480	24000	0.995	-	-
1.8557	24100	0.928	-	-
1.8634	24200	0.9516	-	-
1.8711	24300	0.9325	-	-
1.8788	24400	0.9464	-	-
1.8865	24500	0.9906	-	-
1.8942	24600	0.9571	-	-
1.9019	24700	0.9935	-	-
1.9096	24800	0.9618	-	-
1.9173	24900	0.9829	-	-
1.9250	25000	0.9809	0.0008	0.0002
1.9327	25100	0.9387	-	-
1.9404	25200	0.917	-	-
1.9481	25300	0.9369	-	-
1.9558	25400	0.9699	-	-
1.9635	25500	0.9221	-	-
1.9712	25600	0.9824	-	-
1.9789	25700	0.8855	-	-
1.9866	25800	0.9697	-	-
1.9943	25900	0.9228	-	-
2.0020	26000	0.9275	-	-
2.0097	26100	0.958	-	-
2.0174	26200	0.8973	-	-
2.0251	26300	0.9343	-	-
2.0328	26400	0.883	-	-
2.0405	26500	0.9601	-	-
2.0482	26600	0.9425	-	-
2.0559	26700	1.021	-	-
2.0636	26800	0.9278	-	-
2.0713	26900	0.9386	-	-
2.0790	27000	0.9764	-	-
2.0867	27100	0.925	-	-
2.0944	27200	0.9208	-	-
2.1021	27300	0.9279	-	-
2.1098	27400	0.8847	-	-
2.1175	27500	0.8909	-	-
2.1252	27600	0.9254	-	-
2.1329	27700	1.0138	-	-
2.1406	27800	0.9448	-	-
2.1483	27900	0.9065	-	-
2.1560	28000	0.9136	-	-
2.1637	28100	0.9526	-	-
2.1714	28200	0.9256	-	-
2.1791	28300	0.9488	-	-
2.1868	28400	0.9401	-	-
2.1945	28500	0.9395	-	-
2.2022	28600	0.9867	-	-
2.2099	28700	0.8856	-	-
2.2176	28800	0.9149	-	-
2.2253	28900	0.9182	-	-
2.2330	29000	0.9511	-	-
2.2407	29100	0.9131	-	-
2.2484	29200	0.9676	-	-
2.2561	29300	0.943	-	-
2.2638	29400	0.9085	-	-
2.2715	29500	0.9482	-	-
2.2792	29600	0.9097	-	-
2.2869	29700	0.9163	-	-
2.2946	29800	1.0698	-	-
2.3023	29900	0.9424	-	-
2.3100	30000	0.8987	0.0008	0.0002
2.3177	30100	0.8962	-	-
2.3254	30200	0.9159	-	-
2.3331	30300	0.9313	-	-
2.3408	30400	0.9215	-	-
2.3485	30500	0.9176	-	-
2.3562	30600	0.8948	-	-
2.3639	30700	0.9506	-	-
2.3716	30800	0.9143	-	-
2.3793	30900	0.8499	-	-
2.3870	31000	0.8512	-	-
2.3947	31100	0.928	-	-
2.4024	31200	0.9057	-	-
2.4101	31300	0.863	-	-
2.4178	31400	0.9824	-	-
2.4255	31500	0.9589	-	-
2.4332	31600	0.9438	-	-
2.4409	31700	0.9193	-	-
2.4486	31800	0.9176	-	-
2.4563	31900	0.9242	-	-
2.4640	32000	0.8905	-	-
2.4717	32100	0.8934	-	-
2.4794	32200	0.9231	-	-
2.4871	32300	0.948	-	-
2.4948	32400	0.9178	-	-
2.5025	32500	1.0069	-	-
2.5102	32600	0.9357	-	-
2.5179	32700	0.8841	-	-
2.5256	32800	0.9122	-	-
2.5333	32900	0.8759	-	-
2.5410	33000	0.9003	-	-
2.5487	33100	0.8665	-	-
2.5564	33200	0.9255	-	-
2.5641	33300	0.887	-	-
2.5718	33400	0.9116	-	-
2.5795	33500	0.997	-	-
2.5872	33600	0.8727	-	-
2.5949	33700	0.9501	-	-
2.6026	33800	0.8852	-	-
2.6103	33900	0.9295	-	-
2.6180	34000	0.8793	-	-
2.6257	34100	0.9015	-	-
2.6334	34200	0.8703	-	-
2.6411	34300	0.9449	-	-
2.6488	34400	0.9439	-	-
2.6565	34500	0.9604	-	-
2.6642	34600	0.9389	-	-
2.6719	34700	0.9201	-	-
2.6796	34800	0.897	-	-
2.6873	34900	0.8741	-	-
2.695	35000	0.9243	0.0006	0.0002
2.7027	35100	0.8399	-	-
2.7104	35200	0.9568	-	-
2.7181	35300	0.9171	-	-
2.7258	35400	0.9152	-	-
2.7335	35500	0.871	-	-
2.7412	35600	0.858	-	-
2.7489	35700	0.8877	-	-
2.7566	35800	0.9051	-	-
2.7643	35900	0.9346	-	-
2.7720	36000	0.986	-	-
2.7797	36100	0.9011	-	-
2.7874	36200	0.9499	-	-
2.7951	36300	0.8941	-	-
2.8028	36400	0.9289	-	-
2.8105	36500	0.9183	-	-
2.8182	36600	0.8895	-	-
2.8259	36700	0.9279	-	-
2.8336	36800	0.8905	-	-
2.8413	36900	0.891	-	-
2.8490	37000	0.9369	-	-
2.8567	37100	0.898	-	-
2.8644	37200	0.8794	-	-
2.8721	37300	0.8872	-	-
2.8798	37400	0.9092	-	-
2.8875	37500	0.922	-	-
2.8952	37600	0.8868	-	-
2.9029	37700	0.9268	-	-
2.9106	37800	0.916	-	-
2.9183	37900	0.9022	-	-
2.9260	38000	0.9577	-	-
2.9337	38100	0.8648	-	-
2.9414	38200	0.9534	-	-
2.9491	38300	0.8822	-	-
2.9568	38400	0.9001	-	-
2.9645	38500	0.9153	-	-
2.9722	38600	0.8883	-	-
2.9799	38700	0.8841	-	-
2.9876	38800	0.9036	-	-
2.9953	38900	0.8942	-	-

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.12.12
• Sentence Transformers: 5.1.2
• Transformers: 4.57.1
• PyTorch: 2.9.0+cu126
• Accelerate: 1.11.0
• Datasets: 4.0.0
• Tokenizers: 0.22.1

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}
}