Add new SentenceTransformer model

9ebf9bd verified 8 months ago

47.1 kB

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:44288
  - loss:MultipleNegativesRankingLoss
base_model: BAAI/bge-base-en-v1.5
widget:
  - source_sentence: What past president of the Barcelona club committed suicide in 1930?
    sentences:
      - >-
        In 1978, Josep Lluís Núñez became the first elected president of FC
        Barcelona, and, since then, the members of Barcelona have elected the
        club president. The process of electing a president of FC Barcelona was
        closely tied to Spain's transition to democracy in 1974 and the end of
        Franco's dictatorship. The new president's main objective was to develop
        Barcelona into a world-class club by giving it stability both on and off
        the pitch. His presidency was to last for 22 years, and it deeply
        affected the image of Barcelona, as Núñez held to a strict policy
        regarding wages and discipline, letting go of such players as Maradona,
        Romário and Ronaldo rather than meeting their demands.
      - >-
        On 14 June 1925, in a spontaneous reaction against Primo de Rivera's
        dictatorship, the crowd in the stadium jeered the Royal March. As a
        reprisal, the ground was closed for six months and Gamper was forced to
        relinquish the presidency of the club. This coincided with the
        transition to professional football, and, in 1926, the directors of
        Barcelona publicly claimed, for the first time, to operate a
        professional football club. On 3 July 1927, the club held a second
        testimonial match for Paulino Alcántara, against the Spanish national
        team. To kick off the match, local journalist and pilot Josep Canudas
        dropped the ball onto the pitch from his airplane. In 1928, victory in
        the Spanish Cup was celebrated with a poem titled "Oda a Platko", which
        was written by a member of the Generation of '27, Rafael Alberti,
        inspired by the heroic performance of the Barcelona goalkeeper, Franz
        Platko. On 23 June 1929, Barcelona won the inaugural Spanish League. A
        year after winning the championship, on 30 July 1930, Gamper committed
        suicide after a period of depression brought on by personal and
        financial problems.
      - >-
        In 2003 a congressional committee called the FBI's organized crime
        informant program "one of the greatest failures in the history of
        federal law enforcement." The FBI allowed four innocent men to be
        convicted of the March 1965 gangland murder of Edward "Teddy" Deegan in
        order to protect Vincent Flemmi, an FBI informant. Three of the men were
        sentenced to death (which was later reduced to life in prison), and the
        fourth defendant was sentenced to life in prison. Two of the four men
        died in prison after serving almost 30 years, and two others were
        released after serving 32 and 36 years. In July 2007, U.S. District
        Judge Nancy Gertner in Boston found the bureau helped convict the four
        men using false witness account by mobster Joseph Barboza. The U.S.
        Government was ordered to pay $100 million in damages to the four
        defendants.
  - source_sentence: The MBTA is also known as the what?
    sentences:
      - >-
        Towards the end of the season, Randy Jackson, the last remaining of the
        original judges, announced that he would no longer serve as a judge to
        pursue other business ventures. Both judges Mariah Carey and Nicki Minaj
        also decided to leave after one season to focus on their music careers.
      - >-
        With nearly a third of Bostonians using public transit for their commute
        to work, Boston has the fifth-highest rate of public transit usage in
        the country. Boston's subway system, the Massachusetts Bay
        Transportation Authority (MBTA—known as the "T") operates the oldest
        underground rapid transit system in the Americas, and is the
        fourth-busiest rapid transit system in the country, with 65.5 miles (105
        km) of track on four lines. The MBTA also operates busy bus and commuter
        rail networks, and water shuttles.
      - >-
        With nearly a third of Bostonians using public transit for their commute
        to work, Boston has the fifth-highest rate of public transit usage in
        the country. Boston's subway system, the Massachusetts Bay
        Transportation Authority (MBTA—known as the "T") operates the oldest
        underground rapid transit system in the Americas, and is the
        fourth-busiest rapid transit system in the country, with 65.5 miles (105
        km) of track on four lines. The MBTA also operates busy bus and commuter
        rail networks, and water shuttles.
  - source_sentence: What must a police officer recite to a suspect upon arrest/
    sentences:
      - >-
        In the light of Mother F. A. Forbes research and reference to Pope Saint
        Gregory's writings, it would appear that Athanasius was constrained to
        be Bishop: She writes that when the Patriarch Alexander was on his
        death-bed he called Athanasius, who fled fearing he would be constrained
        to be made Bishop. "When the Bishops of the Church assembled to elect
        their new Patriarch, the whole Catholic population surrounded the
        church, holding up their hands to Heaven and crying; "Give us
        Athanasius!" The Bishops had nothing better. Athanasius was thus
        elected, as Gregory tells us..." (Pope Gregory I, would have full access
        to the Vatican Archives).
      - >-
        The law of criminal procedure in the United States consists of a massive
        overlay of federal constitutional case law interwoven with the federal
        and state statutes that actually provide the foundation for the creation
        and operation of law enforcement agencies and prison systems as well as
        the proceedings in criminal trials. Due to the perennial inability of
        legislatures in the U.S. to enact statutes that would actually force law
        enforcement officers to respect the constitutional rights of criminal
        suspects and convicts, the federal judiciary gradually developed the
        exclusionary rule as a method to enforce such rights. In turn, the
        exclusionary rule spawned a family of judge-made remedies for the abuse
        of law enforcement powers, of which the most famous is the Miranda
        warning. The writ of habeas corpus is often used by suspects and
        convicts to challenge their detention, while the Civil Rights Act of
        1871 and Bivens actions are used by suspects to recover tort damages for
        police brutality.
      - >-
        The law of criminal procedure in the United States consists of a massive
        overlay of federal constitutional case law interwoven with the federal
        and state statutes that actually provide the foundation for the creation
        and operation of law enforcement agencies and prison systems as well as
        the proceedings in criminal trials. Due to the perennial inability of
        legislatures in the U.S. to enact statutes that would actually force law
        enforcement officers to respect the constitutional rights of criminal
        suspects and convicts, the federal judiciary gradually developed the
        exclusionary rule as a method to enforce such rights. In turn, the
        exclusionary rule spawned a family of judge-made remedies for the abuse
        of law enforcement powers, of which the most famous is the Miranda
        warning. The writ of habeas corpus is often used by suspects and
        convicts to challenge their detention, while the Civil Rights Act of
        1871 and Bivens actions are used by suspects to recover tort damages for
        police brutality.
  - source_sentence: If the st belongs to one morpheme, then the stop is what?
    sentences:
      - >-
        They are unaspirated for almost all speakers when immediately following
        word-initial s, as in spill, still, skill. After an s elsewhere in a
        word they are normally unaspirated as well, except sometimes in compound
        words. When the consonants in a cluster like st are analyzed as
        belonging to different morphemes (heteromorphemic) the stop is
        aspirated, but when they are analyzed as belonging to one morpheme the
        stop is unaspirated.[citation needed] For instance, distend has
        unaspirated [t] since it is not analyzed as two morphemes, but distaste
        has an aspirated middle [tʰ] because it is analyzed as dis- + taste and
        the word taste has an aspirated initial t.
      - >-
        The term "Enlightenment" emerged in English in the later part of the
        19th century, with particular reference to French philosophy, as the
        equivalent of the French term 'Lumières' (used first by Dubos in 1733
        and already well established by 1751). From Immanuel Kant's 1784 essay
        "Beantwortung der Frage: Was ist Aufklärung?" ("Answering the Question:
        What is Enlightenment?") the German term became 'Aufklärung' (aufklären
        = to illuminate; sich aufklären = to clear up). However, scholars have
        never agreed on a definition of the Enlightenment, or on its
        chronological or geographical extent. Terms like "les Lumières"
        (French), "illuminismo" (Italian), "ilustración" (Spanish) and
        "Aufklärung" (German) referred to partly overlapping movements. Not
        until the late nineteenth century did English scholars agree they were
        talking about "the Enlightenment."
      - >-
        They are unaspirated for almost all speakers when immediately following
        word-initial s, as in spill, still, skill. After an s elsewhere in a
        word they are normally unaspirated as well, except sometimes in compound
        words. When the consonants in a cluster like st are analyzed as
        belonging to different morphemes (heteromorphemic) the stop is
        aspirated, but when they are analyzed as belonging to one morpheme the
        stop is unaspirated.[citation needed] For instance, distend has
        unaspirated [t] since it is not analyzed as two morphemes, but distaste
        has an aspirated middle [tʰ] because it is analyzed as dis- + taste and
        the word taste has an aspirated initial t.
  - source_sentence: What did the composition of the cardinals consist of?
    sentences:
      - >-
        The largest plaza in Valencia is the Plaza del Ayuntamiento; it is home
        to the City Hall (Ayuntamiento) on its western side and the central post
        office (Edificio de Correos) on its eastern side, a cinema that shows
        classic movies, and many restaurants and bars. The plaza is triangular
        in shape, with a large cement lot at the southern end, normally
        surrounded by flower vendors. It serves as ground zero during the Les
        Falles when the fireworks of the Mascletà can be heard every afternoon.
        There is a large fountain at the northern end.
      - >-
        Pope Sixtus V limited the number of cardinals to 70, comprising six
        cardinal bishops, 50 cardinal priests, and 14 cardinal deacons. Starting
        in the pontificate of Pope John XXIII, that limit has been exceeded. At
        the start of 1971, Pope Paul VI set the number of cardinal electors at a
        maximum of 120, but set no limit on the number of cardinals generally.
        He also established a maximum age of eighty years for electors. His
        action deprived twenty-five living cardinals, including the three living
        cardinals elevated by Pope Pius XI, of the right to participate in a
        conclave.[citation needed] Popes can dispense from church laws and have
        sometimes brought the number of cardinals under the age of 80 to more
        than 120. Pope Paul VI also increased the number of cardinal bishops by
        giving that rank to patriarchs of the Eastern Catholic Churches.
      - >-
        Pope Sixtus V limited the number of cardinals to 70, comprising six
        cardinal bishops, 50 cardinal priests, and 14 cardinal deacons. Starting
        in the pontificate of Pope John XXIII, that limit has been exceeded. At
        the start of 1971, Pope Paul VI set the number of cardinal electors at a
        maximum of 120, but set no limit on the number of cardinals generally.
        He also established a maximum age of eighty years for electors. His
        action deprived twenty-five living cardinals, including the three living
        cardinals elevated by Pope Pius XI, of the right to participate in a
        conclave.[citation needed] Popes can dispense from church laws and have
        sometimes brought the number of cardinals under the age of 80 to more
        than 120. Pope Paul VI also increased the number of cardinal bishops by
        giving that rank to patriarchs of the Eastern Catholic Churches.
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy
model-index:
  - name: SentenceTransformer based on BAAI/bge-base-en-v1.5
    results:
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: gooqa dev
          type: gooqa-dev
        metrics:
          - type: cosine_accuracy
            value: 0.4065999984741211
            name: Cosine Accuracy

SentenceTransformer based on BAAI/bge-base-en-v1.5

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: BAAI/bge-base-en-v1.5
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 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': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, '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})
  (2): Normalize()
)

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("ayushexel/emb-bge-base-en-v1.5-squad-8-epochs")
# Run inference
sentences = [
    'What did the composition of the cardinals consist of?',
    'Pope Sixtus V limited the number of cardinals to 70, comprising six cardinal bishops, 50 cardinal priests, and 14 cardinal deacons. Starting in the pontificate of Pope John XXIII, that limit has been exceeded. At the start of 1971, Pope Paul VI set the number of cardinal electors at a maximum of 120, but set no limit on the number of cardinals generally. He also established a maximum age of eighty years for electors. His action deprived twenty-five living cardinals, including the three living cardinals elevated by Pope Pius XI, of the right to participate in a conclave.[citation needed] Popes can dispense from church laws and have sometimes brought the number of cardinals under the age of 80 to more than 120. Pope Paul VI also increased the number of cardinal bishops by giving that rank to patriarchs of the Eastern Catholic Churches.',
    'Pope Sixtus V limited the number of cardinals to 70, comprising six cardinal bishops, 50 cardinal priests, and 14 cardinal deacons. Starting in the pontificate of Pope John XXIII, that limit has been exceeded. At the start of 1971, Pope Paul VI set the number of cardinal electors at a maximum of 120, but set no limit on the number of cardinals generally. He also established a maximum age of eighty years for electors. His action deprived twenty-five living cardinals, including the three living cardinals elevated by Pope Pius XI, of the right to participate in a conclave.[citation needed] Popes can dispense from church laws and have sometimes brought the number of cardinals under the age of 80 to more than 120. Pope Paul VI also increased the number of cardinal bishops by giving that rank to patriarchs of the Eastern Catholic Churches.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

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

Evaluation

Metrics

Triplet

Dataset: gooqa-dev
Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.4066

Training Details

Training Dataset

Unnamed Dataset

Size: 44,288 training samples
Columns: question, context, and negative

Approximate statistics based on the first 1000 samples:

	question	context	negative
type	string	string	string
details	min: 6 tokens mean: 14.58 tokens max: 37 tokens	min: 34 tokens mean: 150.61 tokens max: 512 tokens	min: 27 tokens mean: 153.22 tokens max: 481 tokens

Samples:

question	context	negative
`How many judges were originally planned for American Idol?`	The show had originally planned on having four judges following the Pop Idol format; however, only three judges had been found by the time of the audition round in the first season, namely Randy Jackson, Paula Abdul and Simon Cowell. A fourth judge, radio DJ Stryker, was originally chosen but he dropped out citing "image concerns". In the second season, New York radio personality Angie Martinez had been hired as a fourth judge but withdrew only after a few days of auditions due to not being comfortable with giving out criticism. The show decided to continue with the three judges format until season eight. All three original judges stayed on the judging panel for eight seasons.	On February 14, 2009, The Walt Disney Company debuted "The American Idol Experience" at its Disney's Hollywood Studios theme park at the Walt Disney World Resort in Florida. In this live production, co-produced by 19 Entertainment, park guests chose from a list of songs and auditioned privately for Disney cast members. Those selected then performed on a stage in a 1000-seat theater replicating the Idol set. Three judges, whose mannerisms and style mimicked those of the real Idol judges, critiqued the performances. Audience members then voted for their favorite performer. There were several preliminary-round shows during the day that culminated in a "finals" show in the evening where one of the winners of the previous rounds that day was selected as the overall winner. The winner of the finals show received a "Dream Ticket" that granted them front-of-the-line privileges at any future American Idol audition. The attraction closed on August 30, 2014.
`What genre of music did season ten American Idol contestant Lauren Alaina sing?`	The two finalists in 2011 were Lauren Alaina and Scotty McCreery, both teenage country singers. McCreery won the competition on May 25, being the youngest male winner and the fourth male in a row to win American Idol. McCreery released his first single, "I Love You This Big", as his coronation song, and Alaina released "Like My Mother Does". McCreery's debut album, Clear as Day, became the first debut album by an Idol winner to reach No. 1 on the US Billboard 200 since Ruben Studdard's Soulful in 2003, and he became the youngest male artist to reach No. 1 on the Billboard 200.	The impact of American Idol is also strongly felt in musical theatre, where many of Idol alumni have forged successful careers. The striking effect of former American Idol contestants on Broadway has been noted and commented on. The casting of a popular Idol contestant can lead to significantly increased ticket sales. Other alumni have gone on to work in television and films, the most notable being Jennifer Hudson who, on the recommendation of the Idol vocal coach Debra Byrd, won a role in Dreamgirls and subsequently received an Academy Award for her performance.
`What was responsible for creating thousands of scientific, technological, and knowledge-based businesses?`	With the emergence and growth of several science parks throughout the world that helped create many thousands of scientific, technological and knowledge-based businesses, Portugal started to develop several science parks across the country. These include the Taguspark (in Oeiras), the Coimbra iParque (in Coimbra), the biocant (in Cantanhede), the Madeira Tecnopolo (in Funchal), Sines Tecnopolo (in Sines), Tecmaia (in Maia) and Parkurbis (in Covilhã). Companies locate in the Portuguese science parks to take advantage of a variety of services ranging from financial and legal advice through to marketing and technological support.	Certain technological inventions of the period – whether of Arab or Chinese origin, or unique European innovations – were to have great influence on political and social developments, in particular gunpowder, the printing press and the compass. The introduction of gunpowder to the field of battle affected not only military organisation, but helped advance the nation state. Gutenberg's movable type printing press made possible not only the Reformation, but also a dissemination of knowledge that would lead to a gradually more egalitarian society. The compass, along with other innovations such as the cross-staff, the mariner's astrolabe, and advances in shipbuilding, enabled the navigation of the World Oceans, and the early phases of colonialism. Other inventions had a greater impact on everyday life, such as eyeglasses and the weight-driven clock.

Loss: MultipleNegativesRankingLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

Size: 5,000 evaluation samples
Columns: question, context, and negative_1

Approximate statistics based on the first 1000 samples:

	question	context	negative_1
type	string	string	string
details	min: 6 tokens mean: 14.64 tokens max: 52 tokens	min: 28 tokens mean: 153.83 tokens max: 510 tokens	min: 28 tokens mean: 152.96 tokens max: 512 tokens

Samples:

question	context	negative_1
`What was the name of the first sulfonamine antibiotic?`	Ehrlich’s approach of systematically varying the chemical structure of synthetic compounds and measuring the effects of these changes on biological activity was pursued broadly by industrial scientists, including Bayer scientists Josef Klarer, Fritz Mietzsch, and Gerhard Domagk. This work, also based in the testing of compounds available from the German dye industry, led to the development of Prontosil, the first representative of the sulfonamide class of antibiotics. Compared to arsphenamine, the sulfonamides had a broader spectrum of activity and were far less toxic, rendering them useful for infections caused by pathogens such as streptococci. In 1939, Domagk received the Nobel Prize in Medicine for this discovery. Nonetheless, the dramatic decrease in deaths from infectious diseases that occurred prior to World War II was primarily the result of improved public health measures such as clean water and less crowded housing, and the impact of anti-infective drugs and vaccines was sign...	The first sulfonamide and first commercially available antibacterial, Prontosil, was developed by a research team led by Gerhard Domagk in 1932 at the Bayer Laboratories of the IG Farben conglomerate in Germany. Domagk received the 1939 Nobel Prize for Medicine for his efforts. Prontosil had a relatively broad effect against Gram-positive cocci, but not against enterobacteria. Research was stimulated apace by its success. The discovery and development of this sulfonamide drug opened the era of antibacterials.
`Who disregarded warnings about dams in the area?`	An article in Science suggested that the construction and filling of the Zipingpu Dam may have triggered the earthquake. The chief engineer of the Sichuan Geology and Mineral Bureau said that the sudden shift of a huge quantity of water into the region could have relaxed the tension between the two sides of the fault, allowing them to move apart, and could have increased the direct pressure on it, causing a violent rupture. The effect was "25 times more" than a year's worth of natural stress from tectonic movement. The government had disregarded warnings about so many large-scale dam projects in a seismically active area. Researchers have been denied access to seismological and geological data to examine the cause of the quake further.	An article in Science suggested that the construction and filling of the Zipingpu Dam may have triggered the earthquake. The chief engineer of the Sichuan Geology and Mineral Bureau said that the sudden shift of a huge quantity of water into the region could have relaxed the tension between the two sides of the fault, allowing them to move apart, and could have increased the direct pressure on it, causing a violent rupture. The effect was "25 times more" than a year's worth of natural stress from tectonic movement. The government had disregarded warnings about so many large-scale dam projects in a seismically active area. Researchers have been denied access to seismological and geological data to examine the cause of the quake further.
`What annual ceremony do Freemasons have?`	The bulk of Masonic ritual consists of degree ceremonies. Candidates for Freemasonry are progressively initiated into Freemasonry, first in the degree of Entered Apprentice. Some time later, in a separate ceremony, they will be passed to the degree of Fellowcraft, and finally they will be raised to the degree of Master Mason. In all of these ceremonies, the candidate is entrusted with passwords, signs and grips peculiar to his new rank. Another ceremony is the annual installation of the Master and officers of the Lodge. In some jurisdictions Installed Master is valued as a separate rank, with its own secrets to distinguish its members. In other jurisdictions, the grade is not recognised, and no inner ceremony conveys new secrets during the installation of a new Master of the Lodge.	Freemasonry consists of fraternal organisations that trace their origins to the local fraternities of stonemasons, which from the end of the fourteenth century regulated the qualifications of stonemasons and their interaction with authorities and clients. The degrees of freemasonry retain the three grades of medieval craft guilds, those of Apprentice, Journeyman or fellow (now called Fellowcraft), and Master Mason. These are the degrees offered by Craft (or Blue Lodge) Freemasonry. Members of these organisations are known as Freemasons or Masons. There are additional degrees, which vary with locality and jurisdiction, and are usually administered by different bodies than the craft degrees.

Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 128
per_device_eval_batch_size: 128
num_train_epochs: 8
warmup_ratio: 0.1
fp16: True
batch_sampler: no_duplicates

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: 128
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: 5e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 8
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: 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: False
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
tp_size: 0
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
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
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
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	gooqa-dev_cosine_accuracy
-1	-1	-	-	0.3564
0.2890	100	0.7631	0.8236	0.3766
0.5780	200	0.4816	0.7701	0.3962
0.8671	300	0.4197	0.7316	0.4012
1.1561	400	0.3274	0.7281	0.4104
1.4451	500	0.2834	0.7302	0.4078
1.7341	600	0.2677	0.7327	0.4036
2.0231	700	0.2654	0.7161	0.4122
2.3121	800	0.1517	0.7344	0.4094
2.6012	900	0.1558	0.7256	0.4174
2.8902	1000	0.1604	0.7256	0.4110
3.1792	1100	0.1214	0.7413	0.4110
3.4682	1200	0.1024	0.7434	0.4124
3.7572	1300	0.1064	0.7384	0.4126
4.0462	1400	0.1024	0.7465	0.4114
4.3353	1500	0.0742	0.7551	0.4180
4.6243	1600	0.0756	0.7664	0.4128
4.9133	1700	0.0761	0.7566	0.4136
5.2023	1800	0.0645	0.7629	0.4126
5.4913	1900	0.0589	0.7709	0.4160
5.7803	2000	0.061	0.7709	0.4122
6.0694	2100	0.0575	0.7735	0.4116
6.3584	2200	0.0484	0.7798	0.4134
6.6474	2300	0.0503	0.7820	0.4098
6.9364	2400	0.0505	0.7778	0.4086
7.2254	2500	0.0449	0.7826	0.4100
7.5145	2600	0.0449	0.7838	0.4082
7.8035	2700	0.0442	0.7864	0.4070
-1	-1	-	-	0.4066

Framework Versions

Python: 3.11.0
Sentence Transformers: 4.0.1
Transformers: 4.50.3
PyTorch: 2.6.0+cu124
Accelerate: 1.5.2
Datasets: 3.5.0
Tokenizers: 0.21.1

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",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}