johnnyboycurtis/ModernBERT-small-sts

ModernBERT-small for General Purpose Similarity

This is a sentence-transformers model trained on the nli, quora, natural_questions, stsb, sentence_compression, simple_wiki, altlex, coco_captions, flickr30k_captions, yahoo_answers and stack_exchange datasets. 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.

This model is based on the wide architecture of johnnyboycurtis/ModernBERT-small

small_modernbert_config = ModernBertConfig(
    hidden_size=384,                 # A common dimension for small embedding models
    num_hidden_layers=12,               # Significantly fewer layers than the base's 22
    num_attention_heads=6,             # Must be a divisor of hidden_size
    intermediate_size=1536,            # 4 * hidden_size -- VERY WIDE!!
    max_position_embeddings=1024,       # Max sequence length for the model; originally 8192
)

model = ModernBertModel(modernbert_small_config)

Model Details

Model Description

• Model Type: Sentence Transformer
• Maximum Sequence Length: 1024 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity
• Training Datasets:
  • nli
  • quora
  • natural_questions
  • stsb
  • sentence_compression
  • simple_wiki
  • altlex
  • coco_captions
  • flickr30k_captions
  • yahoo_answers
  • stack_exchange
• Language: en
• License: apache-2.0

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': 1024, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
  (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("sentence_transformers_model_id")
# Run inference
queries = [
    "A sleeping baby in a pink striped outfit.",
]
documents = [
    'A little baby cradled in someones arms.',
    'A group of hikers traveling along a rock strewn creek bed.',
    'Three young men and a young woman wearing sneakers are leaping in midair at the top of a flight of concrete stairs.',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 384] [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.5804,  0.0193, -0.1261]])

Evaluation

Metrics

Triplet

• Dataset: all-nli-dev
• Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.8808

Semantic Similarity

• Dataset: sts-dev
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.829
spearman_cosine	0.8276

Training Details

Training Datasets

nli

nli

• Dataset: nli at d482672
• Size: 557,850 training samples
• Columns: anchor, positive, and negative
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative
  type	string	string	string
  details	min: 7 tokens mean: 10.46 tokens max: 46 tokens	min: 6 tokens mean: 12.91 tokens max: 40 tokens	min: 5 tokens mean: 13.49 tokens max: 51 tokens

• Samples:

  anchor	positive	negative
  A person on a horse jumps over a broken down airplane.	A person is outdoors, on a horse.	A person is at a diner, ordering an omelette.
  Children smiling and waving at camera	There are children present	The kids are frowning
  A boy is jumping on skateboard in the middle of a red bridge.	The boy does a skateboarding trick.	The boy skates down the sidewalk.

• Loss: CachedMultipleNegativesSymmetricRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 64
  }
  

quora

quora

• Dataset: quora at 451a485
• Size: 101,762 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: 13.85 tokens max: 42 tokens	min: 6 tokens mean: 13.63 tokens max: 44 tokens	min: 4 tokens mean: 14.68 tokens max: 61 tokens

• Samples:

  anchor	positive	negative
  Why in India do we not have one on one political debate as in USA?	Why cant we have a public debate between politicians in India like the one in US?	Can people on Quora stop India Pakistan debate? We are sick and tired seeing this everyday in bulk?
  What is OnePlus One?	How is oneplus one?	Why is OnePlus One so good?
  Does our mind control our emotions?	How do smart and successful people control their emotions?	How can I control my positive emotions for the people whom I love but they don't care about me?

• Loss: CachedMultipleNegativesSymmetricRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 64
  }
  

natural_questions

natural_questions

• Dataset: natural_questions at f9e894e
• Size: 100,231 training samples
• Columns: query and answer
• Approximate statistics based on the first 1000 samples:

  	query	answer
  type	string	string
  details	min: 10 tokens mean: 12.47 tokens max: 23 tokens	min: 17 tokens mean: 138.32 tokens max: 556 tokens

• Samples:

  query	answer
  when did richmond last play in a preliminary final	Richmond Football Club Richmond began 2017 with 5 straight wins, a feat it had not achieved since 1995. A series of close losses hampered the Tigers throughout the middle of the season, including a 5-point loss to the Western Bulldogs, 2-point loss to Fremantle, and a 3-point loss to the Giants. Richmond ended the season strongly with convincing victories over Fremantle and St Kilda in the final two rounds, elevating the club to 3rd on the ladder. Richmond's first final of the season against the Cats at the MCG attracted a record qualifying final crowd of 95,028; the Tigers won by 51 points. Having advanced to the first preliminary finals for the first time since 2001, Richmond defeated Greater Western Sydney by 36 points in front of a crowd of 94,258 to progress to the Grand Final against Adelaide, their first Grand Final appearance since 1982. The attendance was 100,021, the largest crowd to a grand final since 1986. The Crows led at quarter time and led by as many as 13, but the Tig...
  who sang what in the world's come over you	Jack Scott (singer) At the beginning of 1960, Scott again changed record labels, this time to Top Rank Records.[1] He then recorded four Billboard Hot 100 hits – "What in the World's Come Over You" (#5), "Burning Bridges" (#3) b/w "Oh Little One" (#34), and "It Only Happened Yesterday" (#38).[1] "What in the World's Come Over You" was Scott's second gold disc winner.[6] Scott continued to record and perform during the 1960s and 1970s.[1] His song "You're Just Gettin' Better" reached the country charts in 1974.[1] In May 1977, Scott recorded a Peel session for BBC Radio 1 disc jockey, John Peel.
  who produces the most wool in the world	Wool Global wool production is about 2 million tonnes per year, of which 60% goes into apparel. Wool comprises ca 3% of the global textile market, but its value is higher owing to dying and other modifications of the material.[1] Australia is a leading producer of wool which is mostly from Merino sheep but has been eclipsed by China in terms of total weight.[30] New Zealand (2016) is the third-largest producer of wool, and the largest producer of crossbred wool. Breeds such as Lincoln, Romney, Drysdale, and Elliotdale produce coarser fibers, and wool from these sheep is usually used for making carpets.

• Loss: CachedMultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 64
  }
  

stsb

stsb

• Dataset: stsb at ab7a5ac
• Size: 5,749 training samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 6 tokens mean: 10.16 tokens max: 28 tokens	min: 6 tokens mean: 10.12 tokens max: 25 tokens	min: 0.0 mean: 0.45 max: 1.0

• Samples:

  sentence1	sentence2	score
  A plane is taking off.	An air plane is taking off.	1.0
  A man is playing a large flute.	A man is playing a flute.	0.76
  A man is spreading shreded cheese on a pizza.	A man is spreading shredded cheese on an uncooked pizza.	0.76

• Loss: CoSENTLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "pairwise_cos_sim"
  }
  

sentence_compression

sentence_compression

• Dataset: sentence_compression at 605bc91
• Size: 180,000 training samples
• Columns: text and simplified
• Approximate statistics based on the first 1000 samples:

  	text	simplified
  type	string	string
  details	min: 12 tokens mean: 33.95 tokens max: 127 tokens	min: 5 tokens mean: 11.56 tokens max: 29 tokens

• Samples:

  text	simplified
  The USHL completed an expansion draft on Monday as 10 players who were on the rosters of USHL teams during the 2009-10 season were selected by the League's two newest entries, the Muskegon Lumberjacks and Dubuque Fighting Saints.	USHL completes expansion draft
  Major League Baseball Commissioner Bud Selig will be speaking at St. Norbert College next month.	Bud Selig to speak at St. Norbert College
  It's fresh cherry time in Michigan and the best time to enjoy this delicious and nutritious fruit.	It's cherry time

• Loss: CachedMultipleNegativesSymmetricRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 64
  }
  

simple_wiki

simple_wiki

• Dataset: simple_wiki at 60fd9b4
• Size: 102,225 training samples
• Columns: text and simplified
• Approximate statistics based on the first 1000 samples:

  	text	simplified
  type	string	string
  details	min: 9 tokens mean: 35.55 tokens max: 173 tokens	min: 8 tokens mean: 29.29 tokens max: 135 tokens

• Samples:

  text	simplified
  The greatest example has been in his present job ( then , Minister for Foreign Affairs ) , where he has perforce concentrated on Anglo-Irish relations and , in particular the North ( i.e. , Northern Ireland ) .	The greatest example has been in his present job ( then , Minister for Foreign Affairs ) , where he has perforce concentrated on Anglo-Irish relations and , in particular Northern Ireland ( .
  His reputation rose further when opposition leaders under parliamentary privilege alleged that Taoiseach Charles Haughey , who in January 1982 had been Leader of the Opposition , had not merely rung the President 's Office but threatened to end the career of the army officer who took the call and who , on Hillery 's explicit instructions , had refused to put through the call to the President .	President Hillery refused to speak to any opposition party politicians , but when Charles Haughey , who was Leader of the Opposition , had rang the President 's Office he threatened to end the career of the army officer answered and refused on Hillery 's explicit orders to put the call through to the President .
  He considered returning to medicine , perhaps moving with his wife , Maeve ( also a doctor ) to Africa .	He thought about returning to medicine , perhaps moving with his wife , Maeve ( also a doctor ) to Africa .

• Loss: CachedMultipleNegativesSymmetricRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 64
  }
  

altlex

altlex

• Dataset: altlex at 97eb209
• Size: 112,696 training samples
• Columns: text and simplified
• Approximate statistics based on the first 1000 samples:

  	text	simplified
  type	string	string
  details	min: 9 tokens mean: 32.19 tokens max: 121 tokens	min: 6 tokens mean: 26.81 tokens max: 115 tokens

• Samples:

  text	simplified
  A set of 31 guns , cast 1729-1749 by the first master founder at the Royal Foundry , later the Royal Arsenal , Woolwich , were used to fire salutes until 1907 , often for Queen Victoria , who was a frequent visitor .	A set of 31 guns , cast 1729-1749 by the first master founder at the Royal Foundry , later the Royal Arsenal , Woolwich , were used to fire salutes until 1907 , often for Queen Victoria who was a frequent visitor .
  In 1929 , the building became vacant , and was given to Prince Edward , Prince of Wales , by his father , King George V . This became the Prince 's chief residence and was used extensively by him for entertaining and as a country retreat .	In 1929 , the building became vacant , and was given to Prince Edward , the Prince of Wales by his father , King George V . This became the Prince 's chief residence , and was used extensively by the Prince for entertaining and as a country retreat .
  Additions included an octagon room in the north-east side , in which the King regularly had dinner .	Additions included an octagon room in the North-East side , where the King regularly had dinner .

• Loss: CachedMultipleNegativesSymmetricRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 64
  }
  

coco_captions

coco_captions

• Dataset: coco_captions at bd26018
• Size: 414,010 training samples
• Columns: caption1 and caption2
• Approximate statistics based on the first 1000 samples:

  	caption1	caption2
  type	string	string
  details	min: 10 tokens mean: 13.8 tokens max: 27 tokens	min: 10 tokens mean: 13.8 tokens max: 27 tokens

• Samples:

  caption1	caption2
  A clock that blends in with the wall hangs in a bathroom.	A very clean and well decorated empty bathroom
  A very clean and well decorated empty bathroom	A bathroom with a border of butterflies and blue paint on the walls above it.
  A bathroom with a border of butterflies and blue paint on the walls above it.	An angled view of a beautifully decorated bathroom.

• Loss: CachedMultipleNegativesSymmetricRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 64
  }
  

flickr30k_captions

flickr30k_captions

• Dataset: flickr30k_captions at 0ef0ce3
• Size: 158,881 training samples
• Columns: caption1 and caption2
• Approximate statistics based on the first 1000 samples:

  	caption1	caption2
  type	string	string
  details	min: 6 tokens mean: 16.41 tokens max: 64 tokens	min: 6 tokens mean: 16.41 tokens max: 64 tokens

• Samples:

  caption1	caption2
  Two men in green shirts are standing in a yard.	Two young, White males are outside near many bushes.
  Two young, White males are outside near many bushes.	Two young guys with shaggy hair look at their hands while hanging out in the yard.
  Two young guys with shaggy hair look at their hands while hanging out in the yard.	A man in a blue shirt standing in a garden.

• Loss: CachedMultipleNegativesSymmetricRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 64
  }
  

yahoo_answers

yahoo_answers

• Dataset: yahoo_answers at 93b3605
• Size: 599,417 training samples
• Columns: question and answer
• Approximate statistics based on the first 1000 samples:

  	question	answer
  type	string	string
  details	min: 12 tokens mean: 57.04 tokens max: 309 tokens	min: 14 tokens mean: 115.16 tokens max: 992 tokens

• Samples:

  question	answer
  why doesn't an optical mouse work on a glass table? or even on some surfaces?	why doesn't an optical mouse work on a glass table? Optical mice use an LED and a camera to rapidly capture images of the surface beneath the mouse. The infomation from the camera is analyzed by a DSP (Digital Signal Processor) and used to detect imperfections in the underlying surface and determine motion. Some materials, such as glass, mirrors or other very shiny, uniform surfaces interfere with the ability of the DSP to accurately analyze the surface beneath the mouse. \nSince glass is transparent and very uniform, the mouse is unable to pick up enough imperfections in the underlying surface to determine motion. Mirrored surfaces are also a problem, since they constantly reflect back the same image, causing the DSP not to recognize motion properly. When the system is unable to see surface changes associated with movement, the mouse will not work properly.
  What is the best off-road motorcycle trail ? long-distance trail throughout CA	What is the best off-road motorcycle trail ? i hear that the mojave road is amazing! \nsearch for it online.
  What is Trans Fat? How to reduce that? I heard that tras fat is bad for the body. Why is that? Where can we find it in our daily food?	What is Trans Fat? How to reduce that? Trans fats occur in manufactured foods during the process of partial hydrogenation, when hydrogen gas is bubbled through vegetable oil to increase shelf life and stabilize the original polyunsatured oil. The resulting fat is similar to saturated fat, which raises "bad" LDL cholesterol and can lead to clogged arteries and heart disease. \nUntil very recently, food labels were not required to list trans fats, and this health risk remained hidden to consumers. In early July, FDA regulations changed, and food labels will soon begin identifying trans fat content in processed foods.

• Loss: CachedMultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 64
  }
  

stack_exchange

stack_exchange

• Dataset: stack_exchange at 1c9657a
• Size: 304,525 training samples
• Columns: title1 and title2
• Approximate statistics based on the first 1000 samples:

  	title1	title2
  type	string	string
  details	min: 4 tokens mean: 14.71 tokens max: 56 tokens	min: 5 tokens mean: 15.48 tokens max: 71 tokens

• Samples:

  title1	title2
  what is the advantage of using the GPU rendering options in Android?	Can anyone explain all these Developer Options?
  Blank video when converting uncompressed AVI files with ffmpeg	FFmpeg lossy compression problems
  URL Rewriting of a query string in php	How to create friendly URL in php?

• Loss: CachedMultipleNegativesSymmetricRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 64
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 128
• learning_rate: 0.0005
• weight_decay: 0.01
• lr_scheduler_type: cosine
• warmup_ratio: 0.05
• bf16: True
• bf16_full_eval: 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: 128
• 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: 0.0005
• 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: cosine
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.05
• 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: True
• 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
• 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: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Click to expand

Epoch	Step	Training Loss	all-nli-dev_cosine_accuracy	sts-dev_spearman_cosine
0.0243	500	2.0912	-	-
0.0485	1000	1.4267	-	-
0.0728	1500	1.2426	-	-
0.0970	2000	1.0654	0.8136	0.7436
0.1213	2500	0.8238	-	-
0.1456	3000	0.8801	-	-
0.1698	3500	0.7807	-	-
0.1941	4000	0.7651	0.8284	0.7611
0.2183	4500	0.6838	-	-
0.2426	5000	0.6796	-	-
0.2668	5500	0.6014	-	-
0.2911	6000	0.5967	0.8360	0.7741
0.3154	6500	0.6318	-	-
0.3396	7000	0.5821	-	-
0.3639	7500	0.5258	-	-
0.3881	8000	0.6353	0.8463	0.7951
0.4124	8500	0.5788	-	-
0.4367	9000	0.5956	-	-
0.4609	9500	0.5453	-	-
0.4852	10000	0.5218	0.8522	0.7960
0.5094	10500	0.4546	-	-
0.5337	11000	0.5363	-	-
0.5580	11500	0.5055	-	-
0.5822	12000	0.5157	0.8574	0.8133
0.6065	12500	0.4474	-	-
0.6307	13000	0.5242	-	-
0.6550	13500	0.4406	-	-
0.6792	14000	0.4766	0.8628	0.8055
0.7035	14500	0.5492	-	-
0.7278	15000	0.4667	-	-
0.7520	15500	0.401	-	-
0.7763	16000	0.4805	0.8662	0.8041
0.8005	16500	0.4524	-	-
0.8248	17000	0.5427	-	-
0.8491	17500	0.44	-	-
0.8733	18000	0.4774	0.8691	0.8126
0.8976	18500	0.3869	-	-
0.9218	19000	0.4031	-	-
0.9461	19500	0.409	-	-
0.9704	20000	0.3779	0.8706	0.8220
0.9946	20500	0.3703	-	-
1.0189	21000	0.3279	-	-
1.0431	21500	0.2885	-	-
1.0674	22000	0.2838	0.8786	0.8185
1.0917	22500	0.3564	-	-
1.1159	23000	0.2787	-	-
1.1402	23500	0.3007	-	-
1.1644	24000	0.3477	0.8759	0.8215
1.1887	24500	0.3176	-	-
1.2129	25000	0.2671	-	-
1.2372	25500	0.3309	-	-
1.2615	26000	0.3487	0.8744	0.8201
1.2857	26500	0.3497	-	-
1.3100	27000	0.2859	-	-
1.3342	27500	0.3018	-	-
1.3585	28000	0.2812	0.8767	0.8229
1.3828	28500	0.3071	-	-
1.4070	29000	0.2609	-	-
1.4313	29500	0.3083	-	-
1.4555	30000	0.3113	0.8782	0.8253
1.4798	30500	0.279	-	-
1.5041	31000	0.3082	-	-
1.5283	31500	0.2824	-	-
1.5526	32000	0.2987	0.8786	0.8256
1.5768	32500	0.3417	-	-
1.6011	33000	0.3075	-	-
1.6253	33500	0.2631	-	-
1.6496	34000	0.2642	0.8773	0.8249
1.6739	34500	0.2804	-	-
1.6981	35000	0.244	-	-
1.7224	35500	0.29	-	-
1.7466	36000	0.251	0.8785	0.8262
1.7709	36500	0.2476	-	-
1.7952	37000	0.2807	-	-
1.8194	37500	0.2558	-	-
1.8437	38000	0.2536	0.8777	0.8285
1.8679	38500	0.2779	-	-
1.8922	39000	0.2567	-	-
1.9165	39500	0.3665	-	-
1.9407	40000	0.27	0.8796	0.8299
1.9650	40500	0.2635	-	-
1.9892	41000	0.2477	-	-
2.0135	41500	0.2386	-	-
2.0377	42000	0.2477	0.8783	0.8284
2.0620	42500	0.2396	-	-
2.0863	43000	0.1781	-	-
2.1105	43500	0.1858	-	-
2.1348	44000	0.1812	0.8791	0.8278
2.1590	44500	0.2185	-	-
2.1833	45000	0.2431	-	-
2.2076	45500	0.1812	-	-
2.2318	46000	0.2301	0.8806	0.8282
2.2561	46500	0.2169	-	-
2.2803	47000	0.2074	-	-
2.3046	47500	0.2229	-	-
2.3289	48000	0.2257	0.8803	0.8276
2.3531	48500	0.1867	-	-
2.3774	49000	0.2276	-	-
2.4016	49500	0.214	-	-
2.4259	50000	0.2085	0.8808	0.8276
2.4501	50500	0.2198	-	-
2.4744	51000	0.231	-	-
2.4987	51500	0.2395	-	-
2.5229	52000	0.2204	0.8808	0.8276
2.5472	52500	0.1864	-	-
2.5714	53000	0.3129	-	-
2.5957	53500	0.2224	-	-
2.6200	54000	0.1839	0.8808	0.8276
2.6442	54500	0.2032	-	-
2.6685	55000	0.246	-	-
2.6927	55500	0.199	-	-
2.7170	56000	0.2089	0.8808	0.8276
2.7413	56500	0.2235	-	-
2.7655	57000	0.2168	-	-
2.7898	57500	0.2063	-	-
2.8140	58000	0.2202	0.8808	0.8276
2.8383	58500	0.2077	-	-
2.8625	59000	0.1876	-	-
2.8868	59500	0.2204	-	-
2.9111	60000	0.2248	0.8808	0.8276
2.9353	60500	0.1974	-	-
2.9596	61000	0.2084	-	-
2.9838	61500	0.2312	-	-

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.11.13
• Sentence Transformers: 5.0.0
• Transformers: 4.53.1
• PyTorch: 2.7.1+cu128
• Accelerate: 1.8.1
• Datasets: 4.0.0
• Tokenizers: 0.21.2

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",
}

CachedMultipleNegativesRankingLoss

@misc{gao2021scaling,
    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
    year={2021},
    eprint={2101.06983},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

CoSENTLoss

@online{kexuefm-8847,
    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
    author={Su Jianlin},
    year={2022},
    month={Jan},
    url={https://kexue.fm/archives/8847},
}