metadata

language:
  - en
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:1995000
  - loss:MultipleNegativesRankingLoss
base_model: sentence-transformers/all-MiniLM-L6-v2
widget:
  - source_sentence: what are the main differences between interphase and the mitotic phase?
    sentences:
      - >-
        It might surprise you, but you're probably wearing plastic clothes. ...
        Many of our clothes contain plastics like polyester, nylon, acrylic and
        polyamide. In fact most new fabrics are made of plastic – up to 64% of
        them. The thing is, every time we wash these materials they shed
        millions of plastic microfibres.
      - >-
        The cell cycle has two major phases: interphase and the mitotic phase
        (Figure 6.3). During interphase, the cell grows and DNA is replicated.
        During the mitotic phase, the replicated DNA and cytoplasmic contents
        are separated and the cell divides.
      - >-
        2: Chipotle *Whole30 Approved* Chipotle is another awesome option that's
        officially Whole30 Approved. They recently introduced Carne Asada and
        Chicken as compliant options in addition to the carnitas (they've been
        compliant for years!), so it's exciting to have three protein options.
  - source_sentence: how much do brides on say yes to the dress get paid?
    sentences:
      - >-
        Cooking with rice So if you're not going to eat rice straight after
        you've cooked it, you need to store it in the fridge — preferably within
        an hour or so, but definitely within four hours. Refrigeration won't
        kill the bacteria but it will slow down their growth.
      - >-
        Five of the most common determinants of demand are the price of the
        goods or service, the income of the buyers, the price of related goods,
        the preference of the buyer, and the population of the buyers.
      - >-
        Brides aren't compensated for being on the show (unless they're named
        Omarosa, that is). Plus, you need to be prepared to spend big on your
        gown. It's not unusual to see people on the show spend more than $10,000
        on a dress.
  - source_sentence: when was the tornado in jarrell tx?
    sentences:
      - >-
        The Chiefs were overwhelmed by the Bills and lost the game by a score of
        30–13. The Chiefs' victory on January 16, 1994, against the Oilers
        remained the franchise's last post-season victory for 21 years until
        their 30–0 victory over the Houston Texans on January 9, 2016.
      - >-
        On May 27, 1997, one of the most violent tornadoes in modern U.S.
        history produced close-to-unfathomable damage on the outskirts of
        Jarrell, TX, located about 40 miles north-northeast of Austin. There are
        only a few photos and videos of this monster, but it is a disaster well
        worth remembering.
      - >-
        What is open and closed circulation? In the open circulation, the blood
        is not enclosed in the blood vessels and is pumped into a cavity called
        hemocoel. On the contrary, in the closed circulation, the blood is
        pumped through the vessels separate from the interstitial fluid of the
        body.
  - source_sentence: >-
      what is the relationship between photosynthesis cellular respiration and
      the carbon cycle?
    sentences:
      - >-
        Infected people are most contagious up to about 2 weeks after the cough
        begins. Antibiotics may shorten the amount of time someone is
        contagious. While pertussis vaccines are the most effective tool to
        prevent this disease, no vaccine is 100% effective.
      - >-
        ['Download and launch iTunes on your computer.', 'Click iTunes music
        library to choose the song you want to make as a ringtone.',
        'Right-click the song and choose to Get Info.', 'Click Options to set
        the ringtone volume and start & stop time of the ringtone, and click
        OK.']
      - >-
        Cellular respiration and photosynthesis are important parts of the
        carbon cycle. The carbon cycle is the pathways through which carbon is
        recycled in the biosphere. While cellular respiration releases carbon
        dioxide into the environment, photosynthesis pulls carbon dioxide out of
        the atmosphere.
  - source_sentence: what is usb c ss?
    sentences:
      - >-
        Please do not use any air fresheners or fragrances in the same room as
        guinea pigs. They have a rather small and very sensitive respiratory
        system.
      - >-
        “Global warming” refers to the rise in global temperatures due mainly to
        the increasing concentrations of greenhouse gases in the atmosphere.
        “Climate change” refers to the increasing changes in the measures of
        climate over a long period of time – including precipitation,
        temperature, and wind patterns.
      - >-
        The USB Type-C specification is pretty confusing. ... The standard USB
        logo to identify USB 2.0 ports or slower. "SS" markings, which stand for
        SuperSpeed, to identify USB 3.0 ports, otherwise known as USB 3.1 gen 1.
        "10" markings, which stand for 10 Gbps, to identify USB 3.1 gen 2 ports
        with ultra-fast connectivity.
datasets:
  - sentence-transformers/gooaq
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy
model-index:
  - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
    results:
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: gooqa dev
          type: gooqa-dev
        metrics:
          - type: cosine_accuracy
            value: 0.579800009727478
            name: Cosine Accuracy

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

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the gooaq dataset. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: sentence-transformers/all-MiniLM-L6-v2
Maximum Sequence Length: 256 tokens
Output Dimensionality: 384 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- gooaq
Language: en

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': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (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-all-MiniLM-L6-v2-gooaq-2-epochs")
# Run inference
sentences = [
    'what is usb c ss?',
    'The USB Type-C specification is pretty confusing. ... The standard USB logo to identify USB 2.0 ports or slower. "SS" markings, which stand for SuperSpeed, to identify USB 3.0 ports, otherwise known as USB 3.1 gen 1. "10" markings, which stand for 10 Gbps, to identify USB 3.1 gen 2 ports with ultra-fast connectivity.',
    '“Global warming” refers to the rise in global temperatures due mainly to the increasing concentrations of greenhouse gases in the atmosphere. “Climate change” refers to the increasing changes in the measures of climate over a long period of time – including precipitation, temperature, and wind patterns.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# 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	0.5798

Training Details

Training Dataset

gooaq

Dataset: gooaq at b089f72
Size: 1,995,000 training samples
Columns: question and answer
Approximate statistics based on the first 1000 samples:
question answer
type string string
details
min: 8 tokens
mean: 11.86 tokens
max: 23 tokens

min: 14 tokens
mean: 60.74 tokens
max: 133 tokens

	question	answer
type	string	string
details	min: 8 tokens mean: 11.86 tokens max: 23 tokens	min: 14 tokens mean: 60.74 tokens max: 133 tokens

Samples:

question	answer
`can twine be a noun?`	`noun. a strong thread or string composed of two or more strands twisted together. an act of twining, twisting, or interweaving.`
`what is bo id in nsdl?`	`The demat account number allotted to the beneficiary holder(s) by DP is known as the BO-ID. In CDSL it is 16 digits number. It is an intermediary (an institution) between the investor and the depository.`
`how much does it cost to run an electric fan all night?`	`The average indoor ceiling fan costs around 0.13c to 1.29c per hour to run, or between $1.90 and $18.85 each year. This will depend on the fan's speed settings, how frequently it's used, and the rate you pay on electricity. Like most electrical appliances, a ceiling fan's power is measured in watts.`

Loss: MultipleNegativesRankingLoss with these parameters:

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

Evaluation Dataset

gooaq

Dataset: gooaq at b089f72
Size: 5,000 evaluation samples
Columns: question and answer
Approximate statistics based on the first 1000 samples:
question answer
type string string
details
min: 8 tokens
mean: 11.8 tokens
max: 21 tokens

min: 14 tokens
mean: 60.68 tokens
max: 123 tokens

	question	answer
type	string	string
details	min: 8 tokens mean: 11.8 tokens max: 21 tokens	min: 14 tokens mean: 60.68 tokens max: 123 tokens

Samples:

question	answer
`how much water should a person drink in 8 hours?`	`Health authorities commonly recommend eight 8-ounce glasses, which equals about 2 liters, or half a gallon. This is called the 8×8 rule and is very easy to remember. However, some health gurus believe that you need to sip on water constantly throughout the day, even when you're not thirsty.`
`what does this mean in excel #name?`	`Important: The #NAME? error signifies that something needs to be corrected in the syntax, so when you see the error in your formula, resolve it. Do not use any error-handling functions such as IFERROR to mask the error. To avoid typos in formula names, use the Formula Wizard in Excel.`
`are hydroflask good for the environment?`	`Hydro Flasks are a new fad among many students and adults to help minimize plastic waste in the oceans. Hydro Flasks are great because they use a type of metal called TempShield, which keeps your beverage or food either hot for up to six hours or cold for up to twenty-four hours.`

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: 256
per_device_eval_batch_size: 256
num_train_epochs: 2
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: 256
per_device_eval_batch_size: 256
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: 2
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

Click to expand

Epoch	Step	Training Loss	Validation Loss	gooqa-dev_cosine_accuracy
-1	-1	-	-	0.5368
0.0128	100	0.0762	-	-
0.0257	200	0.0715	-	-
0.0385	300	0.0673	-	-
0.0513	400	0.0664	-	-
0.0642	500	0.0669	-	-
0.0770	600	0.0678	-	-
0.0898	700	0.0656	-	-
0.1027	800	0.0624	-	-
0.1155	900	0.0653	-	-
0.1283	1000	0.0642	0.0447	0.5426
0.1412	1100	0.0641	-	-
0.1540	1200	0.0639	-	-
0.1668	1300	0.0611	-	-
0.1796	1400	0.0616	-	-
0.1925	1500	0.0611	-	-
0.2053	1600	0.0629	-	-
0.2181	1700	0.0636	-	-
0.2310	1800	0.0632	-	-
0.2438	1900	0.064	-	-
0.2566	2000	0.0614	0.0404	0.5424
0.2695	2100	0.0622	-	-
0.2823	2200	0.0574	-	-
0.2951	2300	0.0581	-	-
0.3080	2400	0.0598	-	-
0.3208	2500	0.0555	-	-
0.3336	2600	0.0566	-	-
0.3465	2700	0.0583	-	-
0.3593	2800	0.0574	-	-
0.3721	2900	0.0577	-	-
0.3850	3000	0.056	0.0405	0.5390
0.3978	3100	0.0599	-	-
0.4106	3200	0.0538	-	-
0.4235	3300	0.0559	-	-
0.4363	3400	0.0577	-	-
0.4491	3500	0.0533	-	-
0.4620	3600	0.0528	-	-
0.4748	3700	0.052	-	-
0.4876	3800	0.0523	-	-
0.5004	3900	0.0549	-	-
0.5133	4000	0.0508	0.0377	0.5550
0.5261	4100	0.0519	-	-
0.5389	4200	0.0501	-	-
0.5518	4300	0.0498	-	-
0.5646	4400	0.0522	-	-
0.5774	4500	0.0521	-	-
0.5903	4600	0.0513	-	-
0.6031	4700	0.0509	-	-
0.6159	4800	0.0502	-	-
0.6288	4900	0.052	-	-
0.6416	5000	0.0516	0.0348	0.5540
0.6544	5100	0.0496	-	-
0.6673	5200	0.0491	-	-
0.6801	5300	0.0498	-	-
0.6929	5400	0.0537	-	-
0.7058	5500	0.0492	-	-
0.7186	5600	0.0504	-	-
0.7314	5700	0.0488	-	-
0.7443	5800	0.0474	-	-
0.7571	5900	0.048	-	-
0.7699	6000	0.046	0.0347	0.5596
0.7828	6100	0.0494	-	-
0.7956	6200	0.0482	-	-
0.8084	6300	0.0457	-	-
0.8212	6400	0.05	-	-
0.8341	6500	0.0468	-	-
0.8469	6600	0.0492	-	-
0.8597	6700	0.0463	-	-
0.8726	6800	0.0467	-	-
0.8854	6900	0.0468	-	-
0.8982	7000	0.0455	0.0321	0.5648
0.9111	7100	0.0442	-	-
0.9239	7200	0.0461	-	-
0.9367	7300	0.0441	-	-
0.9496	7400	0.0449	-	-
0.9624	7500	0.0463	-	-
0.9752	7600	0.0435	-	-
0.9881	7700	0.0442	-	-
1.0009	7800	0.0432	-	-
1.0137	7900	0.0396	-	-
1.0266	8000	0.0381	0.0307	0.5700
1.0394	8100	0.0366	-	-
1.0522	8200	0.0374	-	-
1.0651	8300	0.0401	-	-
1.0779	8400	0.0375	-	-
1.0907	8500	0.0378	-	-
1.1036	8600	0.0391	-	-
1.1164	8700	0.0347	-	-
1.1292	8800	0.0383	-	-
1.1421	8900	0.0369	-	-
1.1549	9000	0.0375	0.0305	0.5626
1.1677	9100	0.0386	-	-
1.1805	9200	0.0359	-	-
1.1934	9300	0.0361	-	-
1.2062	9400	0.0358	-	-
1.2190	9500	0.0385	-	-
1.2319	9600	0.0335	-	-
1.2447	9700	0.038	-	-
1.2575	9800	0.0372	-	-
1.2704	9900	0.0364	-	-
1.2832	10000	0.0339	0.0297	0.5766
1.2960	10100	0.0341	-	-
1.3089	10200	0.0375	-	-
1.3217	10300	0.0377	-	-
1.3345	10400	0.0346	-	-
1.3474	10500	0.036	-	-
1.3602	10600	0.034	-	-
1.3730	10700	0.0376	-	-
1.3859	10800	0.0357	-	-
1.3987	10900	0.0362	-	-
1.4115	11000	0.0338	0.0284	0.5786
1.4244	11100	0.0346	-	-
1.4372	11200	0.0346	-	-
1.4500	11300	0.0354	-	-
1.4629	11400	0.0346	-	-
1.4757	11500	0.0344	-	-
1.4885	11600	0.0346	-	-
1.5013	11700	0.0367	-	-
1.5142	11800	0.0339	-	-
1.5270	11900	0.0345	-	-
1.5398	12000	0.0354	0.0284	0.5768
1.5527	12100	0.0323	-	-
1.5655	12200	0.0345	-	-
1.5783	12300	0.0363	-	-
1.5912	12400	0.0353	-	-
1.6040	12500	0.0356	-	-
1.6168	12600	0.0336	-	-
1.6297	12700	0.0349	-	-
1.6425	12800	0.0343	-	-
1.6553	12900	0.0361	-	-
1.6682	13000	0.0362	0.0272	0.5792
1.6810	13100	0.0335	-	-
1.6938	13200	0.0327	-	-
1.7067	13300	0.0343	-	-
1.7195	13400	0.0339	-	-
1.7323	13500	0.0332	-	-
1.7452	13600	0.0338	-	-
1.7580	13700	0.0353	-	-
1.7708	13800	0.034	-	-
1.7837	13900	0.0337	-	-
1.7965	14000	0.0336	0.0274	0.5784
1.8093	14100	0.0355	-	-
1.8221	14200	0.0334	-	-
1.8350	14300	0.0307	-	-
1.8478	14400	0.0333	-	-
1.8606	14500	0.0323	-	-
1.8735	14600	0.0319	-	-
1.8863	14700	0.0323	-	-
1.8991	14800	0.0332	-	-
1.9120	14900	0.0331	-	-
1.9248	15000	0.0339	0.0266	0.5786
1.9376	15100	0.0335	-	-
1.9505	15200	0.0328	-	-
1.9633	15300	0.0319	-	-
1.9761	15400	0.0348	-	-
1.9890	15500	0.0336	-	-
-1	-1	-	-	0.5798

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}
}