metadata

base_model: microsoft/mpnet-base
datasets:
  - sentence-transformers/natural-questions
language:
  - en
library_name: sentence-transformers
license: apache-2.0
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
  - dot_accuracy@1
  - dot_accuracy@3
  - dot_accuracy@5
  - dot_accuracy@10
  - dot_precision@1
  - dot_precision@3
  - dot_precision@5
  - dot_precision@10
  - dot_recall@1
  - dot_recall@3
  - dot_recall@5
  - dot_recall@10
  - dot_ndcg@10
  - dot_mrr@10
  - dot_map@100
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:100231
  - loss:ImprovedContrastiveLoss
widget:
  - source_sentence: when did the british leave new york city
    sentences:
      - "Golden State Warriors The Golden State Warriors are an American professional basketball team based in Oakland, California. The Warriors compete in the National Basketball Association (NBA) as a member of the league's Western Conference Pacific Division. The Warriors play their home games at the Oracle Arena in Oakland. The Warriors have reached nine NBA Finals, winning five NBA championships in 1947,[b] 1956, 1975, 2015 and 2017. Golden State's five NBA championships are tied for fourth-most in NBA history with the San Antonio Spurs, and behind only the Boston Celtics (17), Los Angeles Lakers (16) and Chicago Bulls (6). As of 2017, the Warriors are the third most valuable NBA franchise according to Forbes, with an estimated value of $2.6Â\_billion.[6]"
      - >-
        Evacuation Day (New York) Evacuation Day on November 25 marks the day in
        1783 when British troops departed from New York City on Manhattan
        Island, after the end of the American Revolutionary War. After this
        British Army evacuation, General George Washington triumphantly led the
        Continental Army from his former headquarters, north of the city, across
        the Harlem River south down Manhattan through the town to The Battery at
        the foot of Broadway.[1]
      - >-
        Biochemical oxygen demand BOD can be used as a gauge of the
        effectiveness of wastewater treatment plants. It is listed as a
        conventional pollutant in the U.S. Clean Water Act.[2]
  - source_sentence: what is the newest generation of the ipad
    sentences:
      - >-
        Alex Karev Alex is fired by Dr. Lebackes when Maggie Pierce accidentally
        reveals to him that Karev was thinking about leaving the job. Webber
        recommended Bailey to fill Yang's board seat after she left, so Bailey
        and Alex fight over the chair. They both make presentations to the board
        and eventually Bailey wins, with a unanimous vote in her favor. He is
        hired back as an attending Peds surgeon and takes over full-time as
        Arizona pursues a fellowship with Dr. Herman. Alex continues to date Jo
        and his friendship with Meredith grows stronger than ever, with him
        taking on the role of her new person. When Derek dies and Meredith runs
        away, Alex is upset by her leaving without telling him where she went
        and calls her everyday. Eventually she calls him, tells him she is okay,
        and to stop calling. When she goes into labor and gives birth to Ellis
        Shepherd, Alex goes to see her since he is her emergency contact. He
        brings Meredith and her kids back to her house. She asks to move back in
        with him in her old house. Alex sells Meredith back the house and he and
        Jo rent a loft.
      - "List of presidents of the United States by age The median age upon accession to the presidency is 55 years and 3 months. This is how old Lyndon B. Johnson was at the time of his inauguration. The youngest person to assume the office was Theodore Roosevelt, who became president at the age of 42\_years, 322\_days, following William McKinley's assassination; the oldest was Donald Trump, who was 70\_years, 220\_days old at his inauguration. The youngest person to be elected president was John F. Kennedy, at 43\_years, 163\_days of age on election day; the oldest was Ronald Reagan, who was 73\_years, 274\_days old at the time of his election to a second term."
      - >-
        iPad (2018) The iPad (officially sixth-generation iPad) is a 9.7-inch
        (25cm) tablet computer designed, developed, and marketed by Apple Inc.
        It was announced on March 27, 2018 during an education-focused event in
        Chicago and it is a revision of the 2017 model, upgraded with the Apple
        A10 Fusion SoC and support for styluses such as Apple Pencil.[2] The
        iPad is marketed towards educators and schools.
  - source_sentence: what is the average speed of passenger airplane
    sentences:
      - >-
        Fixed exchange-rate system In the 21st century, the currencies
        associated with large economies typically do not fix or peg exchange
        rates to other currencies. The last large economy to use a fixed
        exchange rate system was the People's Republic of China which, in July
        2005, adopted a slightly more flexible exchange rate system called a
        managed exchange rate.[2] The European Exchange Rate Mechanism is also
        used on a temporary basis to establish a final conversion rate against
        the Euro (â‚¬) from the local currencies of countries joining the
        Eurozone.
      - >-
        Tenth Doctor The Tenth Doctor is an incarnation of the Doctor, the
        protagonist of the BBC science fiction television programme Doctor Who,
        who is played by David Tennant in three series as well as nine specials.
        As with previous incarnations of the Doctor, the character has also
        appeared in other Doctor Who spin-offs. In the programme's narrative,
        the Doctor is a centuries-old Time Lord alien from the planet Gallifrey
        who travels in time in his TARDIS, frequently with companions. When the
        Doctor is critically injured beyond medical repair, he can regenerate
        his body; in doing so, his physical appearance and personality change,
        and a new actor assumes the role. Tennant's portrayal of the Doctor is
        of an outwardly charismatic and charming adventurer whose likable and
        easygoing attitude can quickly turn to righteous fury when provoked.
      - >-
        Cruise (aeronautics) The typical cruising airspeed for a long-distance
        commercial passenger aircraft is approximately 475–500 knots (878–926
        km/h; 546–575 mph).
  - source_sentence: when is cars three going to be released
    sentences:
      - >-
        Benedict's reagent The color of the obtained precipitate gives an idea
        about the quantity of sugar present in the solution, hence the test is
        semi-quantitative. A greenish precipitate indicates about 0.5 g%
        concentration; yellow precipitate indicates 1 g% concentration; orange
        indicates 1.5 g% and red indicates 2 g% or higher concentration.
      - >-
        Cars 3 The film was released on June 16, 2017, has grossed over $362
        million worldwide and received generally positive reviews, with many
        critics considering it an improvement over its predecessor, as well as
        praising its emotional story and animation.[7]
      - >-
        Sleeping Beauty At the christening of a king and queen's long-wished-for
        child, seven good fairies are invited to be godmothers to the infant
        princess. The fairies attend the banquet at the palace. Each fairy is
        presented with a golden plate and drinking cups adorned with jewels.
        Soon after, an old fairy enters the palace and is seated with a plate of
        fine china and a crystal drinking glass. This old fairy is overlooked
        because she has been within a tower for many years and everyone had
        believed her to be deceased. Six of the other seven fairies then offer
        their gifts of beauty, wit, grace, dance, song, and goodness to the
        infant princess. The evil fairy is very angry about having been
        forgotten, and as her gift, enchants the infant princess so that she
        will one day prick her finger on a spindle of a spinning wheel and die.
        The seventh fairy, who hasn't yet given her gift, attempts to reverse
        the evil fairy's curse. However, she can only do so partially. Instead
        of dying, the Princess will fall into a deep sleep for 100 years and be
        awakened by a kiss from a king's son.
  - source_sentence: who was ancient china's main enemy that lived to the north
    sentences:
      - >-
        Betty Lynn Elizabeth Ann Theresa "Betty" Lynn[1] (born August 29, 1926)
        is a former American actress. She is best known for her role as Thelma
        Lou, Deputy Barney Fife's girlfriend, on The Andy Griffith Show.
      - >-
        Sampath Bank Sampath Bank PLC is a licensed commercial bank incorporated
        in Sri Lanka in 1986 with 229 branches and 373 ATMs island wide. It has
        won the "Bank of the Year" award by "The Banker" of Financial Times
        Limited â€“ London, for the second consecutive year and the "National
        Business Excellence Awards 2010".[citation needed] It has become the
        third largest private sector bank in Sri Lanka with Rs. 453 billion in
        deposits as of 30 June 2016.[1]
      - >-
        Sui dynasty The Sui Dynasty (Chinese: 隋朝; pinyin: Suí cháo) was a
        short-lived imperial dynasty of China of pivotal significance. The Sui
        unified the Northern and Southern dynasties and reinstalled the rule of
        ethnic Han Chinese in the entirety of China proper, along with
        sinicization of former nomadic ethnic minorities (the Five Barbarians)
        within its territory. It was succeeded by the Tang dynasty, which
        largely inherited its foundation.
co2_eq_emissions:
  emissions: 171.00505800984172
  energy_consumed: 0.4399387140015789
  source: codecarbon
  training_type: fine-tuning
  on_cloud: false
  cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
  ram_total_size: 31.777088165283203
  hours_used: 1.139
  hardware_used: 1 x NVIDIA GeForce RTX 3090
model-index:
  - name: MPNet base trained on Natural Questions pairs
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: natural questions dev
          type: natural-questions-dev
        metrics:
          - type: cosine_accuracy@1
            value: 0.5886032645880168
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8148763561724172
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8832958655067931
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9410614798162448
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.5886032645880168
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.27162545205747235
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17665917310135862
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09410614798162449
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.5886032645880168
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8148763561724172
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8832958655067931
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9410614798162448
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.769304304207993
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7136417796519368
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7163262351468975
            name: Cosine Map@100
          - type: dot_accuracy@1
            value: 0.5153943896002345
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.7485094321180725
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.8219137914182387
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.8932655654383735
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.5153943896002345
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2495031440393575
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.16438275828364773
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08932655654383737
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.5153943896002345
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.7485094321180725
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.8219137914182387
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.8932655654383735
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.7056782708639685
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6453053511503243
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.6498747716288641
            name: Dot Map@100

MPNet base trained on Natural Questions pairs

This is a sentence-transformers model finetuned from microsoft/mpnet-base on the natural-questions dataset. 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: microsoft/mpnet-base
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- natural-questions
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': 512, 'do_lower_case': False}) with Transformer model: MPNetModel 
  (1): Pooling({'word_embedding_dimension': 768, '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("tomaarsen/mpnet-base-natural-questions-icl")
# Run inference
sentences = [
    "who was ancient china's main enemy that lived to the north",
    'Sui dynasty The Sui Dynasty (Chinese: 隋朝; pinyin: Suí cháo) was a short-lived imperial dynasty of China of pivotal significance. The Sui unified the Northern and Southern dynasties and reinstalled the rule of ethnic Han Chinese in the entirety of China proper, along with sinicization of former nomadic ethnic minorities (the Five Barbarians) within its territory. It was succeeded by the Tang dynasty, which largely inherited its foundation.',
    'Sampath Bank Sampath Bank PLC is a licensed commercial bank incorporated in Sri Lanka in 1986 with 229 branches and 373 ATMs island wide. It has won the "Bank of the Year" award by "The Banker" of Financial Times Limited â€“ London, for the second consecutive year and the "National Business Excellence Awards 2010".[citation needed] It has become the third largest private sector bank in Sri Lanka with Rs. 453 billion in deposits as of 30 June 2016.[1]',
]
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

Information Retrieval

Dataset: natural-questions-dev
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.5886
cosine_accuracy@3	0.8149
cosine_accuracy@5	0.8833
cosine_accuracy@10	0.9411
cosine_precision@1	0.5886
cosine_precision@3	0.2716
cosine_precision@5	0.1767
cosine_precision@10	0.0941
cosine_recall@1	0.5886
cosine_recall@3	0.8149
cosine_recall@5	0.8833
cosine_recall@10	0.9411
cosine_ndcg@10	0.7693
cosine_mrr@10	0.7136
cosine_map@100	0.7163
dot_accuracy@1	0.5154
dot_accuracy@3	0.7485
dot_accuracy@5	0.8219
dot_accuracy@10	0.8933
dot_precision@1	0.5154
dot_precision@3	0.2495
dot_precision@5	0.1644
dot_precision@10	0.0893
dot_recall@1	0.5154
dot_recall@3	0.7485
dot_recall@5	0.8219
dot_recall@10	0.8933
dot_ndcg@10	0.7057
dot_mrr@10	0.6453
dot_map@100	0.6499

Training Details

Training Dataset

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: 11.74 tokens
max: 21 tokens

min: 17 tokens
mean: 135.66 tokens
max: 512 tokens

	query	answer
type	string	string
details	min: 10 tokens mean: 11.74 tokens max: 21 tokens	min: 17 tokens mean: 135.66 tokens max: 512 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 Tigers took over the game as it progressed and scored seven straight goals at one point. They eventually would win by 48 points – 16.12 (108) to Adelaide's 8.12 (60) – to end their 37-year flag drought.[22] Dustin Martin also became the first player to win a Premiership medal, the Brownlow Medal and the Norm Smith Medal in the same season, while Damien Hardwick was named AFL Coaches Association Coach of the Year. Richmond's jump from 13th to premiers also marked the biggest jump from one AFL season to the next.
`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: main.ImprovedContrastiveLoss with these parameters:
```
{
    "temperature": 0.01
}
```

Evaluation Dataset

natural-questions

Dataset: natural-questions at f9e894e
Size: 100,231 evaluation samples
Columns: query and answer
Approximate statistics based on the first 1000 samples:
query answer
type string string
details
min: 10 tokens
mean: 11.79 tokens
max: 25 tokens

min: 15 tokens
mean: 142.78 tokens
max: 512 tokens

	query	answer
type	string	string
details	min: 10 tokens mean: 11.79 tokens max: 25 tokens	min: 15 tokens mean: 142.78 tokens max: 512 tokens

Samples:

query	answer
`who betrayed siraj ud daula in the battle of plassey in 1757`	Siraj ud-Daulah The Battle of Plassey (or Palashi) is widely considered the turning point in the history of the subcontinent, and opened the way to eventual British domination. After Siraj-ud-Daulah's conquest of Calcutta, the British sent fresh troops from Madras to recapture the fort and avenge the attack. A retreating Siraj-ud-Daulah met the British at Plassey. He had to make camp 27 miles away from Murshidabad. On 23 June 1757 Siraj-ud-Daulah called on Mir Jafar because he was saddened by the sudden fall of Mir Mardan who was a very dear companion of Siraj in battles. The Nawab asked for help from Mir Jafar. Mir Jafar advised Siraj to retreat for that day. The Nawab made the blunder in giving the order to stop the fight. Following his command, the soldiers of the Nawab were returning to their camps. At that time, Robert Clive attacked the soldiers with his army. At such a sudden attack, the army of Siraj became indisciplined and could think of no way to fight. So all fled away in such a situation. Betrayed by a conspiracy plotted by Jagat Seth, Mir Jafar, Krishna Chandra, Omichund etc., he lost the battle and had to escape. He went first to Murshidabad and then to Patna by boat, but was eventually arrested by Mir Jafar's soldiers.
`what is the meaning of single malt whisky`	`Single malt whisky Single malt whisky is malt whisky from a single distillery, that is, whisky distilled from fermented mash made exclusively with malted grain (usually barley), as distinguished from unmalted grain.`
`when is despicable me 3 going to release`	Despicable Me 3 Despicable Me 3 premiered on June 14, 2017, at the Annecy International Animated Film Festival, and was released in the United States on June 30, 2017, by Universal Pictures in 3D, RealD 3D, Dolby Cinema, and IMAX 3D. The film received mixed reviews from critics[7] and has grossed over $1 billion worldwide, making it the third highest-grossing film of 2017, the fifth highest-grossing animated film of all time and the 28th highest-grossing overall. It is Illumination's second film to gross over $1 billion, after Minions in 2015, becoming the first ever animated franchise to do so.

Loss: main.ImprovedContrastiveLoss with these parameters:
```
{
    "temperature": 0.01
}
```

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
learning_rate: 2e-05
num_train_epochs: 1
warmup_ratio: 0.1
bf16: 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: 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
learning_rate: 2e-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: 1
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: True
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: 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}
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: False
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
dispatch_batches: None
split_batches: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	natural-questions-dev_cosine_map@100
0	0	-	-	0.1228
0.0004	1	12.7798	-	-
0.0355	100	3.9819	1.0786	0.5069
0.0711	200	0.9481	0.8211	0.6407
0.1066	300	0.8286	0.8080	0.6565
0.1422	400	0.8069	0.7917	0.6608
0.1777	500	0.8148	0.7781	0.6778
0.2133	600	0.7887	0.7719	0.6790
0.2488	700	0.7866	0.7651	0.6817
0.2844	800	0.7848	0.7768	0.6836
0.3199	900	0.7702	0.7628	0.6863
0.3555	1000	0.7774	0.7558	0.6987
0.3910	1100	0.7537	0.7630	0.6871
0.4266	1200	0.7588	0.7524	0.7012
0.4621	1300	0.7688	0.7544	0.6942
0.4977	1400	0.7454	0.7567	0.6910
0.5332	1500	0.7371	0.7498	0.7047
0.5688	1600	0.7581	0.7529	0.6953
0.6043	1700	0.7922	0.7465	0.6967
0.6399	1800	0.7528	0.7474	0.7021
0.6754	1900	0.7572	0.7482	0.7048
0.7110	2000	0.7384	0.7460	0.7050
0.7465	2100	0.7523	0.7439	0.7069
0.7821	2200	0.7587	0.7437	0.7072
0.8176	2300	0.7416	0.7424	0.7080
0.8532	2400	0.7407	0.7416	0.7112
0.8887	2500	0.7634	0.7397	0.7125
0.9243	2600	0.7513	0.7383	0.7137
0.9598	2700	0.7392	0.7383	0.7149
0.9954	2800	0.7398	0.7379	0.7147
1.0	2813	-	-	0.7163

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.440 kWh
Carbon Emitted: 0.171 kg of CO2
Hours Used: 1.139 hours

Training Hardware

On Cloud: No
GPU Model: 1 x NVIDIA GeForce RTX 3090
CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
RAM Size: 31.78 GB

Framework Versions

Python: 3.11.6
Sentence Transformers: 3.1.0.dev0
Transformers: 4.41.2
PyTorch: 2.3.1+cu121
Accelerate: 0.31.0
Datasets: 2.20.0
Tokenizers: 0.19.1

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}