Instructions to use much1na/distil-cohere-v1-ckpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use much1na/distil-cohere-v1-ckpt with sentence-transformers:

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("much1na/distil-cohere-v1-ckpt")

sentences = [
"In many of the works, including the original series, Warhol drastically simplified the gold medallion that appears on Campbell's Soup cans by replacing the paired allegorical figures with a flat yellow disk. In most variations, the only hint of three-dimensionality came from the shading on the tin lid. Otherwise the image was flat. The works with torn labels are perceived as metaphors of life in the sense that even packaged food must meet its end. They are often described as expressionistic.\nThe great variety of work produced using a semi-mechanized process with many collaborators, Warhol's popularity, the value of his works, and the diversity of works across various genre and media have created a need for the Andy Warhol Art Authentication Board to certify the authenticity of works by Warhol.\nThe Andy Warhol Museum of Modern Art had one of its Campbell's Soup Cans paintings stolen. It was estimated to have been worth €35,000 (€ in ). The theft occurred in March 2015, but it was not made public until August 2015. In March 2021 in Manhattan, a Campbell's Soup Cans lithograph worth tens of thousands of dollars was stolen from art curator Gil Traub. Although the thief was identified on security video, the artwork was not recovered.",
"A notable remix artist is Bally Sagoo, a Punjabi-Sikh, Anglo-Indian raised in Birmingham, England. Sagoo described his music as \"a bit of tablas, a bit of the Indian sound. But bring on the bass lines, bring on the funky-drummer beat, bring on the James Brown samples\", to Time magazine in 1997. He was recently signed by Sony. Daler Mehndi, a Punjabi singer from India has a type of music known as \"folk pop\". Mehndi has released tracks such as \"Bolo Ta Ra Ra\" and \"Ho Jayegee Balle Balle\". His song \"Tunak Tunak Tun\" was released in 1998.\nCanada and the United States\nPunjabi immigrants have encouraged the growth of Punjabi folk music in the Western hemisphere rather than bhangra music. The bhangra industry has grown in North America much less than in the United Kingdom.\nNorth American (non bhangra) folk artists such as Manmohan Waris, Jazzy Bains, Kamal Heer, Harbhajan Mann, Sarabjit Cheema, and Debi Makhsoospuri have emerged and the remix market has grown.\nIn 2001, Punjabi folk, and its hip-hop form, folkhop, began to exert an influence over US R&B music, when Missy Elliott released the folkhop-influenced song \"Get Ur Freak On\". In 2003, a version of Panjabi MC's \"Mundian To Bach Ke\" (\"Beware of the Boys\") featured U.S. rapper Jay-Z. Additionally, American rapper Pras of The Fugees recorded tracks with British alternative bhangra band Swami. American singer and actress Selena Gomez released her bhangra-influenced single \"Come & Get It\" from her first solo album Stars Dance in 2013.",
"Harm resulting from untreated eosinophilia potentially varies with cause. During an allergic reaction, the release of histamine from mast cells causes vasodilation which allows eosinophils to migrate from the blood and localize in affected tissues. Accumulation of eosinophils in tissues can be significantly damaging. Eosinophils, like other granulocytes, contain granules (or sacs) filled with digestive enzymes and cytotoxic proteins which under normal conditions are used to destroy parasites but in eosinophilia these agents can damage healthy tissues. In addition to these agents, the granules in eosinophils also contain inflammatory molecules and cytokines which can recruit more eosinophils and other inflammatory cells to the area and hence amplify and perpetuate the damage. This process is generally accepted to be the major inflammatory process in the pathophysiology of atopic or allergic asthma.\nDiagnosis\nDiagnosis is by complete blood count (CBC). However, in some cases, a more accurate absolute eosinophil count may be needed. Medical history is taken, with emphasis on travel, allergies and drug use. Specific test for causative conditions are performed, often including chest x-ray, urinalysis, liver and kidney function tests, and serologic tests for parasitic and connective tissue diseases. The stool is often examined for traces of parasites (i.e. eggs, larvae, etc.) though a negative test does not rule out parasitic infection; for example, trichinosis requires a muscle biopsy. Elevated serum B12 or low white blood cell alkaline phosphatase, or leukocytic abnormalities in a peripheral smear indicates a disorder of myeloproliferation. In cases of idiopathic eosinophilia, the patient is followed for complications. A brief trial of corticosteroids can be diagnostic for allergic causes, as the eosinophilia should resolve with suppression of the immune over-response. Neoplastic disorders are diagnosed through the usual methods, such as bone marrow aspiration and biopsy for the leukemias, MRI/CT to look for solid tumors, and tests for serum LDH and other tumor markers.",
"The Holden Commodore (VP) is a full-size car that was produced by Holden from 1991 to 1993. It was the second iteration of the second generation of the Commodore. Its range included the luxury variants, Holden Berlina (VP) and Holden Calais (VP)."
]
embeddings = model.encode(sentences)

similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4]

Notebooks
Google Colab
Kaggle

SentenceTransformer based on google/bert_uncased_L-6_H-512_A-8

This is a sentence-transformers model finetuned from google/bert_uncased_L-6_H-512_A-8 on the parquet dataset. It maps sentences & paragraphs to a 512-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: google/bert_uncased_L-6_H-512_A-8
Maximum Sequence Length: 512 tokens
Output Dimensionality: 512 dimensions
Similarity Function: Cosine Similarity
Supported Modality: Text
Training Dataset:
- parquet

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
  (1): Pooling({'embedding_dimension': 512, 'pooling_mode': 'mean', '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
sentences = [
    'Just 320 FFs were constructed and production ceased in 1971.\nOther projects\nAustin A40 Sports: As one in a series of collaborations between Austin and Jensen, the Austin A40 Sports originated when Austin\'s chairman Leonard Lord, upon seeing the Interceptor, requested that Jensen, and their designer Eric Neale, develop a body that could use the A40 mechanicals.\nThe resulting body-on-frame A40 Sports\xa0– which debuted at the 1949 London Motor Show\xa0– had been designed by Eric Neale, an ex-Wolseley stylist who had joined Jensen in 1946. During production, the A40 Sports\' aluminium bodies were built by Jensen and transported to Austin\'s Longbridge plant for final assembly. The A40 Sports had been intended as more of a sporty touring car and not a sports car per se, and over 4000 examples were manufactured from 1951 to 1953.\nAustin-Healey 100: Although Jensen\'s design for a new Austin-based sports-car was rejected by the British Motor Corporation (BMC) in 1952 in favour of a design provided by Donald Healey, Jensen did win the BMC contract to build the bodies for the resultant Austin-Healey 100 and the rest of the "big Healey" cars. At the end of 1960 Austin-Healey cars occupied about 350 of the 850 men in Jensen\'s factory.',
    'Joshua Steele\'s disagreement, and subsequent correspondence, with Monboddo over details of the "melody and measure of speech" resulted in Steele\'s Prosodia Rationalis, a foundational work both in phonetics and in the analysis of verse rhythm.\nEvolutionary theorist\nMonboddo is considered by some scholars as a precursive thinker in the theory of evolution. However, some modern evolutionary historians do not give Monboddo an equally high standing in the influence of history of evolutionary thought.\n"Monboddo: Scottish jurist and pioneer anthropologist who explored the origins of language and society and anticipated principles of Darwinian evolution."\n"With some wavering, he extended Rousseau\'s doctrine of the identity of species of man and the chimp into the hypothesis of common descent of all the anthropoids, and suggested by implication a general law of evolution." Lovejoy.\nCharles Neaves, one of Monboddo\'s successors on the high court of Scotland, believed that proper credit was not given to Monboddo in evolutionary theory development. Neaves wrote in verse:\nThough Darwin now proclaims the law\nAnd spreads it far abroad, O!\nThe man that first the secret saw\nWas honest old Monboddo.\nThe architect precedence takes\nOf him that bears the hod, O!\nSo up and at them, Land of Cakes,',
    'As a consequence, in May 1833 Ozanam and a group of other young men founded the charitable Society of Saint Vincent de Paul, which already by the time of his death numbered upwards of 2,000 members. The founding members developed their method of service under the guidance of Sister Rosalie Rendu, a member of the Congregation of Daughters of Charity of Saint Vincent de Paul, who was prominent in serving the poor in the slums of Paris. The members of the conferences collaborated with Rendu during the time of the cholera epidemic. When fear had gripped the population, she organized the conferences in all the neighborhoods of Paris to care for the cholera victims, becoming well known in the city for her work, especially in the 12th arrondissement. Frederic\'s first act of charity was to take his supply of winter firewood and bring it to a widow whose husband had died of cholera.\nOzanam received the degrees of Bachelor of Laws in 1834, Bachelor of Arts in 1835 and Doctor of Laws in 1836. His father, who had wanted him to study law, died on 12 May 1837. Although he preferred literature, Ozanam worked in the legal profession in order to support his mother, and was admitted to the Bar in Lyon in 1837.\nIn 1835, Ozanam persuaded Monseigneur de Quélen, the Archbishop of Paris, to ask Jean-Baptiste Henri Lacordaire to preach a Lenten series at the Cathedral of Notre-Dame in Paris, as part of the Notre-Dame Lectures specially aimed at the catechesis of Christian youth, which had been inaugurated at the behest of his friend Ozanam. Lacordaire\'s first lecture took place on 8 March 1835, and was met with wide acclaim. Lacordaire was reputed to be the greatest pulpit orator of the nineteenth century. The social event of its day, it was well-attended and became an annual tradition in Paris. According to Thomas Bokenkotter, Lacordaire\'s Notre Dame Conferences, "...proved to be one of the most dramatic events of nineteenth century church history."',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 512]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.1691, 0.1666],
#         [0.1691, 1.0000, 0.3301],
#         [0.1666, 0.3301, 1.0000]])

Training Details

Training Dataset

parquet

Dataset: parquet
Size: 3,810,976 training samples
Columns: text and label
Approximate statistics based on the first 100 samples:
text label
type string list

modality text
details
min: 99 tokens
mean: 314.97 tokens
max: 505 tokens

size: 1024 elements

	text	label
type	string	list
modality	text
details	min: 99 tokens mean: 314.97 tokens max: 505 tokens	size: 1024 elements

Samples:

text	label
Negligent homicide is a criminal charge brought against a person who, through criminal negligence, allows another person to die. Other times, an intentional killing may be negotiated down to this lesser charge as a compromised resolution of a murder case, as might occur in the context of the intentional shooting of an unarmed man after a traffic altercation. Negligent homicide can be distinguished from involuntary manslaughter by its mens rea requirement: negligent homicide requires criminal negligence, while manslaughter requires recklessness.	`[0.07659912109375, -0.01461029052734375, 0.008819580078125, -0.062469482421875, -0.0020580291748046875, ...]`
Latin trap is a subgenre of Latin hip hop music that originated in Puerto Rico. A direct descendant of southern hip hop, and influenced by reggaeton, it gained popularity after 2007, and has since spread throughout Latin America. The trap is slang for a place where drugs are sold. Latin trap is similar to mainstream trap with lyrics about life on la calle (the street), drugs, sex and violence. Characteristics Latin trap is a subgenre of Latin hip hop, taking influence from Southern hip hop as well as Puerto Rican genres like reggaeton and dembow. Vocals include a bend of rapping and singing using synthesizers and voice distorted autotune, often in Spanish, while still maintaining the trap style sonic circuitry. The lyrics in Latin trap are often about street life, violence, sex, drugs, and people who live on the other side of the law and are proud of it. History	`[-0.0191802978515625, -0.0106353759765625, -0.036407470703125, 0.029571533203125, -0.004840850830078125, ...]`
Surface 3 is a 2-in-1 detachable from the Microsoft Surface series, introduced by Microsoft in 2015. Unlike its predecessor, the Surface 2, Surface 3 utilizes an x86 Intel Atom system-on-chip architecture, or SoC, rather than a processor with ARM architecture such as the Nvidia Tegra that powered the Surface 2, and runs standard versions of Windows 8.1 or Windows 10. History The older, original Surface (also known as Surface RT) and Surface 2, with their ARM-based processors and Windows RT operating system, were designed to compete with the iPad and other tablets. The first Surface was criticized for performance issues, which were reduced in the succeeding Surface 2. Due to the differing processors, these devices were incompatible with the vast number of Windows programs written for x86-based computers, running only those written and compiled for Windows RT, loaded from Microsoft's application store.	`[-0.04119873046875, -0.016265869140625, -0.0126800537109375, 0.0103912353515625, -0.0557861328125, ...]`

Loss: EmbedDistillLoss with these parameters:

{
    "distance_metric": "cosine",
    "projection_dim": 1024
}

Evaluation Dataset

parquet

Dataset: parquet
Size: 256 evaluation samples
Columns: text and label
Approximate statistics based on the first 100 samples:
text label
type string list

modality text
details
min: 53 tokens
mean: 308.2 tokens
max: 512 tokens

size: 1024 elements

	text	label
type	string	list
modality	text
details	min: 53 tokens mean: 308.2 tokens max: 512 tokens	size: 1024 elements

Samples:

text	label
Revolution Pro Wrestling (2022–present) Slater made his debut in Revolution Pro Wrestling at RevPro Live In London 64 on August 7, 2022, where he unsuccessfully challenged Luke Jacobs for the Undisputed British Cruiserweight Championship. He continued to make regular appearances in the company's signature events such as the British J-Cup, where he made his first appearance at the 202 edition where he defeated Lio Rush in the first rounds but fell short to Robbie X, Lee Hunter and Will Kaven in a four-way match in the finals which occurred on the same night. One year later, Slater succeeded in winning the cup by defeating Will Kaven in the first rounds ans then Harrison Bennett, Mascara Dorada and Wild Boar in the four-way match of the finals. At RevPro Revolution Rumble 2023 on March 26, Slater competed in the traditional royal rumble match, bout won by Michael Oku and also involving various other notable opponents such as Big Damo, Callum Newman, Eddie Dennis, Gabriel Kidd, Francesco ...	`[-0.026824951171875, 0.03338623046875, 0.011566162109375, 0.01247406005859375, 0.002338409423828125, ...]`
On 9 April 2015, Masagos was promoted to the rank of full Minister but did not have a portfolio yet, so he was a Minister in the Prime Minister's Office. This was the first time in Singaporean history when there were two Malay ministers in the Cabinet, the other being Yaacob Ibrahim. Masagos was also promoted to Second Minister for Home Affairs and Second Minister for Foreign Affairs, and was put in charge of leading the PAP team in Tampines GRC. On the same day, Prime Minister Lee Hsien Loong said that Masagos's elevation to full Minister reflected the "progress of the Malay community" in Singapore. Masagos also said that he was honoured to have been appointed and that "[h]aving two Malay full ministers in the Cabinet for the first time in our nation's history reflects the [Government's] trust and recognition of the good progress made by the Malay-Muslim community". On 1 October 2015, Masagos took up the portfolio of Minister for Environment and Water Resources. From 1 May 2018, he wa...	`[0.039398193359375, -0.022613525390625, 0.006793975830078125, 0.00878143310546875, -0.005939483642578125, ...]`
In the late 15th century the Clan Mackay and Clan Ross had long been at feud. This resulted in the Battle of Tarbat in 1486 where the Mackays were defeated by the Rosses and chief Angus Roy Mackay, 9th of Strathnaver was killed. This was followed by the Battle of Aldy Charrish where the Rosses were defeated by the Mackays and the Ross chief was killed along with many of his clan. According to 17th-century historian Sir Robert Gordon, who was a younger son of Alexander Gordon, 12th Earl of Sutherland, the Clan Sutherland joined the side of the Clan Mackay at this battle. However, 19th-century historian Angus Mackay disputes the Sutherland's presence at the battle stating that it would be unlikely that the Earl of Sutherland at the time would have assisted against the Rosses as he was married to a daughter of the Ross chief of Balnagowan, and also that the feudal superiority of the Sutherlands over the Mackays "nowhere existed save in his own fertile imagination". 16th century and clan c...	`[0.06927490234375, 0.021881103515625, 0.01392364501953125, -0.044342041015625, 0.058258056640625, ...]`

Loss: EmbedDistillLoss with these parameters:

{
    "distance_metric": "cosine",
    "projection_dim": 1024
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 32
max_steps: 100000
learning_rate: 2e-05
lr_scheduler_type: cosine
warmup_steps: 2000
fp16: True
per_device_eval_batch_size: 32
seed: 12

All Hyperparameters

Click to expand

per_device_train_batch_size: 32
num_train_epochs: 3.0
max_steps: 100000
learning_rate: 2e-05
lr_scheduler_type: cosine
lr_scheduler_kwargs: None
warmup_steps: 2000
optim: adamw_torch_fused
optim_args: None
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
optim_target_modules: None
gradient_accumulation_steps: 1
average_tokens_across_devices: True
max_grad_norm: 1.0
label_smoothing_factor: 0.0
bf16: False
fp16: True
bf16_full_eval: False
fp16_full_eval: False
tf32: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
use_liger_kernel: False
liger_kernel_config: None
use_cache: False
neftune_noise_alpha: None
torch_empty_cache_steps: None
auto_find_batch_size: False
log_on_each_node: True
logging_nan_inf_filter: True
include_num_input_tokens_seen: no
log_level: passive
log_level_replica: warning
disable_tqdm: False
project: huggingface
trackio_space_id: None
trackio_bucket_id: None
trackio_static_space_id: None
per_device_eval_batch_size: 32
prediction_loss_only: True
eval_on_start: False
eval_do_concat_batches: True
eval_use_gather_object: False
eval_accumulation_steps: None
include_for_metrics: []
batch_eval_metrics: False
save_only_model: False
save_on_each_node: False
enable_jit_checkpoint: False
push_to_hub: False
hub_private_repo: None
hub_model_id: None
hub_strategy: every_save
hub_always_push: False
hub_revision: None
load_best_model_at_end: False
ignore_data_skip: False
restore_callback_states_from_checkpoint: False
full_determinism: False
seed: 12
data_seed: None
use_cpu: False
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
dataloader_drop_last: True
dataloader_num_workers: 0
dataloader_pin_memory: True
dataloader_persistent_workers: False
dataloader_prefetch_factor: None
remove_unused_columns: True
label_names: None
train_sampling_strategy: random
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
ddp_static_graph: None
ddp_backend: None
ddp_timeout: 1800
fsdp: None
fsdp_config: None
deepspeed: None
debug: []
skip_memory_metrics: True
do_predict: False
resume_from_checkpoint: None
warmup_ratio: None
local_rank: -1
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
1.6460	98010	0.2052	-
1.6461	98020	0.2037	-
1.6463	98030	0.2029	-
1.6465	98040	0.2076	-
1.6466	98050	0.2059	-
1.6468	98060	0.2044	-
1.6470	98070	0.2072	-
1.6471	98080	0.2071	-
1.6473	98090	0.2050	-
1.6475	98100	0.2072	-
1.6476	98110	0.2072	-
1.6478	98120	0.2063	-
1.6480	98130	0.2068	-
1.6481	98140	0.2073	-
1.6483	98150	0.2046	-
1.6485	98160	0.2058	-
1.6486	98170	0.2045	-
1.6488	98180	0.2086	-
1.6490	98190	0.2032	-
1.6491	98200	0.2058	-
1.6493	98210	0.2045	-
1.6495	98220	0.2084	-
1.6496	98230	0.2040	-
1.6498	98240	0.2063	-
1.6500	98250	0.2055	-
1.6502	98260	0.2051	-
1.6503	98270	0.2051	-
1.6505	98280	0.2056	-
1.6507	98290	0.2054	-
1.6508	98300	0.2080	-
1.6510	98310	0.2086	-
1.6512	98320	0.2063	-
1.6513	98330	0.2043	-
1.6515	98340	0.2074	-
1.6517	98350	0.2066	-
1.6518	98360	0.2050	-
1.6520	98370	0.2058	-
1.6522	98380	0.2053	-
1.6523	98390	0.2057	-
1.6525	98400	0.2051	-
1.6527	98410	0.2052	-
1.6528	98420	0.2045	-
1.6530	98430	0.2061	-
1.6532	98440	0.2050	-
1.6533	98450	0.2074	-
1.6535	98460	0.2071	-
1.6537	98470	0.2071	-
1.6538	98480	0.2064	-
1.6540	98490	0.2088	-
1.6542	98500	0.2062	-
1.6544	98510	0.2064	-
1.6545	98520	0.2038	-
1.6547	98530	0.2053	-
1.6549	98540	0.2053	-
1.6550	98550	0.2032	-
1.6552	98560	0.2093	-
1.6554	98570	0.2049	-
1.6555	98580	0.2055	-
1.6557	98590	0.2037	-
1.6559	98600	0.2070	-
1.6560	98610	0.2052	-
1.6562	98620	0.2061	-
1.6564	98630	0.2063	-
1.6565	98640	0.2070	-
1.6567	98650	0.2033	-
1.6569	98660	0.2039	-
1.6570	98670	0.2043	-
1.6572	98680	0.2062	-
1.6574	98690	0.2041	-
1.6575	98700	0.2060	-
1.6577	98710	0.2042	-
1.6579	98720	0.2064	-
1.6580	98730	0.2069	-
1.6582	98740	0.2076	-
1.6584	98750	0.2042	-
1.6585	98760	0.2057	-
1.6587	98770	0.2044	-
1.6589	98780	0.2041	-
1.6591	98790	0.2088	-
1.6592	98800	0.2053	-
1.6594	98810	0.2060	-
1.6596	98820	0.2058	-
1.6597	98830	0.2047	-
1.6599	98840	0.2040	-
1.6601	98850	0.2052	-
1.6602	98860	0.2060	-
1.6604	98870	0.2067	-
1.6606	98880	0.2065	-
1.6607	98890	0.2070	-
1.6609	98900	0.2079	-
1.6611	98910	0.2055	-
1.6612	98920	0.2036	-
1.6614	98930	0.2074	-
1.6616	98940	0.2077	-
1.6617	98950	0.2068	-
1.6619	98960	0.2075	-
1.6621	98970	0.2043	-
1.6622	98980	0.2068	-
1.6624	98990	0.2066	-
1.6626	99000	0.2080	0.2022
1.6627	99010	0.2091	-
1.6629	99020	0.2050	-
1.6631	99030	0.2049	-
1.6633	99040	0.2049	-
1.6634	99050	0.2068	-
1.6636	99060	0.2093	-
1.6638	99070	0.2058	-
1.6639	99080	0.2048	-
1.6641	99090	0.2075	-
1.6643	99100	0.2088	-
1.6644	99110	0.2083	-
1.6646	99120	0.2057	-
1.6648	99130	0.2055	-
1.6649	99140	0.2059	-
1.6651	99150	0.2053	-
1.6653	99160	0.2052	-
1.6654	99170	0.2049	-
1.6656	99180	0.2077	-
1.6658	99190	0.2064	-
1.6659	99200	0.2056	-
1.6661	99210	0.2042	-
1.6663	99220	0.2054	-
1.6664	99230	0.2038	-
1.6666	99240	0.2068	-
1.6668	99250	0.2046	-
1.6669	99260	0.2065	-
1.6671	99270	0.2080	-
1.6673	99280	0.2081	-
1.6675	99290	0.2020	-
1.6676	99300	0.2070	-
1.6678	99310	0.2083	-
1.6680	99320	0.2052	-
1.6681	99330	0.2066	-
1.6683	99340	0.2063	-
1.6685	99350	0.2063	-
1.6686	99360	0.2037	-
1.6688	99370	0.2065	-
1.6690	99380	0.2069	-
1.6691	99390	0.2063	-
1.6693	99400	0.2035	-
1.6695	99410	0.2066	-
1.6696	99420	0.2047	-
1.6698	99430	0.2085	-
1.6700	99440	0.2054	-
1.6701	99450	0.2071	-
1.6703	99460	0.2059	-
1.6705	99470	0.2057	-
1.6706	99480	0.2048	-
1.6708	99490	0.2022	-
1.6710	99500	0.2051	-
1.6711	99510	0.2064	-
1.6713	99520	0.2074	-
1.6715	99530	0.2059	-
1.6716	99540	0.2043	-
1.6718	99550	0.2074	-
1.6720	99560	0.2043	-
1.6722	99570	0.2063	-
1.6723	99580	0.2050	-
1.6725	99590	0.2068	-
1.6727	99600	0.2073	-
1.6728	99610	0.2053	-
1.6730	99620	0.2051	-
1.6732	99630	0.2092	-
1.6733	99640	0.2044	-
1.6735	99650	0.2046	-
1.6737	99660	0.2065	-
1.6738	99670	0.2058	-
1.6740	99680	0.2042	-
1.6742	99690	0.2058	-
1.6743	99700	0.2057	-
1.6745	99710	0.2065	-
1.6747	99720	0.2044	-
1.6748	99730	0.2071	-
1.6750	99740	0.2035	-
1.6752	99750	0.2062	-
1.6753	99760	0.2069	-
1.6755	99770	0.2076	-
1.6757	99780	0.2061	-
1.6758	99790	0.2056	-
1.6760	99800	0.2045	-
1.6762	99810	0.2050	-
1.6764	99820	0.2060	-
1.6765	99830	0.2088	-
1.6767	99840	0.2030	-
1.6769	99850	0.2042	-
1.6770	99860	0.2062	-
1.6772	99870	0.2068	-
1.6774	99880	0.2053	-
1.6775	99890	0.2074	-
1.6777	99900	0.2065	-
1.6779	99910	0.2040	-
1.6780	99920	0.2085	-
1.6782	99930	0.2070	-
1.6784	99940	0.2070	-
1.6785	99950	0.2058	-
1.6787	99960	0.2073	-
1.6789	99970	0.2044	-
1.6790	99980	0.2058	-
1.6792	99990	0.2065	-
1.6794	100000	0.2038	0.2022

Training Time

Training: 11.3 minutes
Evaluation: 1.0 seconds
Total: 11.3 minutes

Framework Versions

Python: 3.12.13
Sentence Transformers: 5.7.0
Transformers: 5.13.1
PyTorch: 2.10.0+cu128
Accelerate: 1.14.0
Datasets: 5.0.1
Tokenizers: 0.22.2

Additional Resources

Training and Finetuning Embedding Models with Sentence Transformers: the end-to-end guide for training or finetuning Sentence Transformer models.
Introduction to Matryoshka Embedding Models: variable-size embeddings that can be truncated with minimal quality loss.
Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval: post-training compression of embedding vectors.
Multimodal Embedding & Reranker Models with Sentence Transformers: use text, image, audio, and video models through the same API.
Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers: train multimodal embedding models, with a Visual Document Retrieval walkthrough.

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",
}

EmbedDistillLoss

@article{kim2023embeddistill,
    title={EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval},
    author={Kim, Seungyeon and Rawat, Ankit Singh and Zaheer, Manzil and Jayasumana, Sadeep and Sadhanala, Veeranjaneyulu and Jitkrittum, Wittawat and Menon, Aditya Krishna and Fergus, Rob and Kumar, Sanjiv},
    year={2023},
    eprint={2301.12005},
    archivePrefix={arXiv},
    primaryClass={cs.IR}
}