ll / README.md

kaamd

Upload folder using huggingface_hub

6a48e45 verified 4 months ago

preview code

raw

history blame contribute delete

44.2 kB

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:14166
  - loss:SparseLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: >-
      Instruct: Given a web search query, retrieve relevant passages that answer
      the query

      Query: Does borrowing from my 401(k) make sense in my specific
      circumstance?
    sentences:
      - >-
        I'm not sure why you think that it matters that the distribution goes to
        an S-Corp vs an individual tax payer. You seem to think it has any
        relevance to your question, but it doesn't. It only confuses your
        readers. The situation is like this: LLC X is deriving income in State
        #2. It has two members (I and S) residents of State #1. Members I and S
        pay all their taxes to State #1, and don't pay taxes to State #2. State
        #2 audited member I and that member now needs to pay back taxes and
        penalties to State #2 on income derived from that State. Your question:
        Does that mean that member S should be worried, since that member was
        essentially doing the exact same thing as member I? My answer: Yes.
      - >-
        Interest rates are market driven. They tend to be based on the prime
        rate set by the federal reserve bank because of the tremendous lending
        capacity of that institution and that other loan originators will often
        fund their own lending (at least in part) with fed loans. However, there
        is no mandatory link between the federal reserve rate and the market
        rate. No law stipulates that rates cannot rise or fall. They will rise
        and fall as lenders see necessary to use their capital. Though a lender
        asking 10% interest might make no loans when others are willing to lend
        for 9%. The only protection you have is that we are (mostly)
        economically free. As a borrower, you are protected by the fact that
        there are many lenders. Likewise, as a lender, because there are many
        borrowers. Stability is simply by virtue of the fact that one market
        participant with inordinate pricing will find fewer counterparties to
        transact.
      - >-
        "You're getting great wisdom and options. Establishing your actionable
        path will require the details that only you know, such as how much is
        actually in each paycheck (and how much tax is withheld), how much do
        you spend each month (and yearly expenses too), how much spending can
        you actually cut or replace, how comfortable are you with considering
        (or not considering) unexpected/emergency spending. You mentioned you
        were cash-poor, but only you know what your current account balances
        are, which will affect your actions and priorities. Btw, interestingly,
        your ""increase 401k contributions by 2% each year"" will need to end
        before hitting the $18K contribution limit. I took some time and added
        the details you posted into a cash-flow program to see your scenario
        over the next few years. There isn't a ""401k loan"" activity in this
        program yet, so I build the scenario from other simple activities. You
        seem financially minded enough to continue modeling on your own. I'm
        posting the more difficult one for you (borrow from 401k), but you'll
        have to input your actual balances, paycheck and spending. My spending
        assumptions must be low, and I entered $70K as ""take-home,"" so the
        model looks like you've got lots of cash. If you choose to play with it,
        then consider modeling some other scenarios from the advice in the other
        posts. Here's the ""Borrow $6500 from 401k"" scenario model at
        Whatll.Be: https://whatll.be/d1x1ndp26i/2 To me, it's all about trying
        the scenarios and see which one seems to work with all of the details.
        The trick is knowing what scenarios to try, and how to model them. Full
        disclosure: I needed to do similar planning, so I wrote Whatll.Be and I
        now share it with other people. It's in beta, so I'm testing it with
        scenarios like yours. (Notice most of the extra activity occurs on
        2018-Jan-01)"
  - source_sentence: >-
      Instruct: Given a web search query, retrieve relevant passages that answer
      the query

      Query: Finding a good small business CPA?
    sentences:
      - >-
        I have had better experiences with accountants in smaller towns.  It
        seems they are used to working with small businesses and their
        reputation is very important to them.
      - >-
        "It's a scam. The cashier's check will be forged. Craigslist has a
        warning about it here (item #3). What kind of payment do you think is
        not fakable? Or at least not   likely to be used in scams? When on
        craigslist - deal only locally and in person. You can ask to see the
        person's ID if you're being paid by check When being paid by check, how
        can seeing his/her ID help? In case the   check isn't cashable, I can
        find that person by keeping record of   his/her ID?  If you're paid by
        check, the payers details should be printed on the check. By checking
        the ID you can verify that the details match (name/address), so you can
        find the payer later. Of course the ID can be faked too, but there's so
        much you can do to protect yourself. You'll get better protection
        (including verified escrow service) by selling on eBay. Is being paid by
        cash the safest way currently,   although cash can be faked too, but it
        is the least common thing that   is faked currently? Do you recommend to
        first deposit the cash into a   bank (so that let the bank verify if the
        cash is faked), before   delivering the good?  For Craigslist, use cash
        and meet locally. That rules out most scams as a seller. What payment
        methods do you think are relatively safe currently?   Then getting
        checks must be the least favorite way of being paid. Do   you think cash
        is better than money order or cashier order?  You should only accept
        cash. If it is a large transaction, you can meet them at your bank, have
        them get cash, and you receive the cash from the bank. Back to the
        quoted scam, how will they later manipulate me? Are they interested in  
        my stuffs on moving sale, or in my money? They will probably
        ""accidentally"" overpay you and ask for a refund of some portion of the
        overpayment. In that case you will be out the entire amount that you
        send back to them and possibly some fees from your bank for cashing a
        bad check."
      - >-
        "Putting them on line 10 is best suited for your situation. According to
        Quickbooks:  Commissions and Fees (Line 10) Commissions/fees paid to
        nonemployees to generate revenue (e.g. agent   fees). It seems like this
        website you are using falls under the term ""nonemployees""."
  - source_sentence: >-
      Instruct: Given a web search query, retrieve relevant passages that answer
      the query

      Query: Are Investment Research websites worth their premiums?
    sentences:
      - >-
        Anyone who claims they can consistently beat the market and asks you to
        pay them to tell you how is a liar. This cannot be done, as the market
        adjusts itself. There's nothing they could possibly learn that analysts
        and institutional investors don't already know. They earn their money
        through the subscription fees, not through capital gains on their
        beat-the-market suggestions, that means that they don't have to rely on
        themselves to earn money, they only need you to rely on them. They have
        to provide proof because they cannot lie in advertisements, but if you
        read carefully, there are many small letters and disclaimers that
        basically remove any liability from them by saying that they don't take
        responsibility for anything and don't guarantee anything.
      - >-
        "I don't see EWQ6 in any of your links, so I can't say for certain, but
        when you buy an option contract on a future, the option will be for a
        specific future (and strike).  So the page you're looking at may be for
        options on E-mini S&P 500 futures in general, and when you actually
        purchase one through your broker, you pick a specific expiry (which will
        be based on the ""prompt"" future, meaning the next future that expires
        after the option) and strike. UPDATE: Based on this page mirror, the
        option EWQ7 is an option on the ESU7 (SEP 2017) future.  The next 3
        monthly options use ESZ7 as the underlier, which confirms that they use
        the next prompt future as the underlier."
      - >-
        There are a few factors at play here. Depending on the bank that has
        offered you the card there are different types of overdraft protection
        that may have been set up. Typically, if they attempt to run the card
        with no money, if one of these is in play, you will be spared any
        overdraft fees by the transaction charging to a designated overdraft
        account, usually savings, or by the transaction failing due to
        insufficient funds.  If you know the transaction went through, and you
        know there were not enough funds in the account to cover the
        transactions, then you have a few options. If you have overdraft
        protection that auto charges insufficient funds charges to a separate
        account, then you have nothing to worry about. If you do not, most banks
        offer a grace period where you have until the end of the day to zero out
        your account, that is to say pay the overdraft amount and bring your
        balance to at least $0.  If this is a charge that occurred in the past,
        and you have already been charged an overdraft fee, there may still be
        hope. I cannot speak for all banks, but I know that Chase Bank offers a
        once per year overdraft forgiveness, where they will get rid of the
        charges if you agree to bring the account out of the negative. There is
        a chance other banks will do the same if you call their customer
        service.
  - source_sentence: >-
      Instruct: Given a web search query, retrieve relevant passages that answer
      the query

      Query: Ballpark salary equivalent today of “healthcare benefits” in the
      US?
    sentences:
      - >-
        While in the interview stage you need one good outfit. Take care of them
        and they will see you through this stage of the process. Shoes, ties,
        shirt, and a suit can all be purchased on sale. The fact that you have
        months before graduation give you time to purchase them when there is a
        sale.  Off-the-rack is good enough for a suit for this stage of your
        life. There is no need to go custom made when you are just starting out.
        In fact you may find you never need more than one or two suits, and they
        never need to be custom made.
      - >-
        Fiduciary They are obligated by the rules of the exchanges they are
        listed with. Furthermore, there is a strong chance that people running
        the company also have stock, so it personally benefits them to create
        higher prices. Finally, maybe they don't care about the prices directly,
        but by being a good company with a good product or service, they are
        desirable and that is expressed as a higher stock price.  Not every
        action is because it will raise the stock price, but because it is good
        for business which happens to make the stock more valuable.
      - >-
        There is some magic involved in that calculation, because what health
        insurance is worth to you is not necessarily the same it is worth for
        the employer. Two examples that illustrate the extreme ends of the
        spectrum: let's say you or a family member have a chronic or a serious
        illness, especially if it is a preexisting condition - for instance,
        cancer. In that case, health insurance can be worth literally millions
        of dollars to you. Even if you are a diabetic, the value of health
        insurance can be substantial. Sometimes, it could even make financial
        sense in that case to accept a very low-paying job. On the other extreme
        of the scale, if you are very young and healthy, many people decide to
        forego insurance. In that case, the value of health insurance can be as
        little as the penalty (usually, 2% of your taxable income, I believe).
  - source_sentence: >-
      Instruct: Given a web search query, retrieve relevant passages that answer
      the query

      Query: I am under 18 years old, in the US, my parents have terrible
      credit, how can I take out a loan?
    sentences:
      - >-
        What about web-hosting fees? Cost of Internet service? Cost of computer
        equipment to do the work? Amortized cost of development? Time for
        support calls/email? Phone service used for sales? Advertising/marketing
        expenses? Look hard--I bet there are some costs.
      - >-
        In the equity markets, the P/E is usually somewhere around 15.  The P/E
        can be viewed as the inverse of the rate of a perpetuity. Since the
        average is 15, and the E/P of that would be 6.7%, r should be 6.7% on
        average. If your business is growing, the growth rate can be
        incorporated like so: As you can see, a high g would make the price
        negative, in essence the seller should actually pay someone to take the
        business, but in reality, r is determined from the p and an estimated g.
        For a business of any growth rate, it's best to compare the multiple to
        the market, so for the average business in the market with your
        business's growth rate and industry, that P/E would be best applied to
        your company's income.
      - >-
        Depending on the state this might not be possible. Loans are considered
        contracts, and various states regulate how minors may enter into them.
        For example, in the state of Oregon, a minor may NOT enter into a
        contract without their parent being on the contract as well. So you are
        forced to wait until you turn 18. At that time you won't have a credit
        history, and to lenders that often is worse than having bad credit. I
        can't help with the car (other than to recommend you buy a junker for
        $500-$1,000 and just live with it for now), but you could certainly get
        a secured credit card or line of credit from your local bank. The way
        they are arranged is, you make a deposit of an amount of your choosing
        (generally at least $200 for credit cards, and $1,000 for lines of
        credit), and receive a revolving line with a limit of that same amount.
        As you use and pay on this loan, it will be reported in your credit
        history. If you start that now, by the time you turn 18 you will have
        much better options for purchasing vehicles.
pipeline_tag: sentence-similarity
library_name: sentence-transformers

SentenceTransformer

This is a sentence-transformers model trained on the fiqa dataset. It maps sentences & paragraphs to a 4096-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
Maximum Sequence Length: 32768 tokens
Output Dimensionality: 4096 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- fiqa

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': 32768, 'do_lower_case': False, 'architecture': 'MistralModel'})
  (1): Pooling({'word_embedding_dimension': 4096, 'pooling_mode_cls_token': False, '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': True, 'include_prompt': True})
  (2): SparseEmbedding(
    (sparsifyer): ZeroNeuron(in_features=4096, out_features=4096)
  )
)

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 = [
    'Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery: I am under 18 years old, in the US, my parents have terrible credit, how can I take out a loan?',
    "Depending on the state this might not be possible. Loans are considered contracts, and various states regulate how minors may enter into them. For example, in the state of Oregon, a minor may NOT enter into a contract without their parent being on the contract as well. So you are forced to wait until you turn 18. At that time you won't have a credit history, and to lenders that often is worse than having bad credit. I can't help with the car (other than to recommend you buy a junker for $500-$1,000 and just live with it for now), but you could certainly get a secured credit card or line of credit from your local bank. The way they are arranged is, you make a deposit of an amount of your choosing (generally at least $200 for credit cards, and $1,000 for lines of credit), and receive a revolving line with a limit of that same amount. As you use and pay on this loan, it will be reported in your credit history. If you start that now, by the time you turn 18 you will have much better options for purchasing vehicles.",
    "In the equity markets, the P/E is usually somewhere around 15.  The P/E can be viewed as the inverse of the rate of a perpetuity. Since the average is 15, and the E/P of that would be 6.7%, r should be 6.7% on average. If your business is growing, the growth rate can be incorporated like so: As you can see, a high g would make the price negative, in essence the seller should actually pay someone to take the business, but in reality, r is determined from the p and an estimated g. For a business of any growth rate, it's best to compare the multiple to the market, so for the average business in the market with your business's growth rate and industry, that P/E would be best applied to your company's income.",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 4096]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.6277, 0.2807],
#         [0.6277, 1.0000, 0.2775],
#         [0.2807, 0.2775, 1.0000]])

Training Details

Training Dataset

fiqa

Dataset: fiqa
Size: 14,166 training samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 24 tokens
mean: 36.38 tokens
max: 62 tokens

min: 2 tokens
mean: 223.61 tokens
max: 1683 tokens

	anchor	positive
type	string	string
details	min: 24 tokens mean: 36.38 tokens max: 62 tokens	min: 2 tokens mean: 223.61 tokens max: 1683 tokens

Samples:

anchor	positive
`Instruct: Given a web search query, retrieve relevant passages that answer the query Query: What is considered a business expense on a business trip?`	The IRS Guidance pertaining to the subject. In general the best I can say is your business expense may be deductible. But it depends on the circumstances and what it is you want to deduct. Travel Taxpayers who travel away from home on business may deduct related expenses, including the cost of reaching their destination, the cost of lodging and meals and other ordinary and necessary expenses. Taxpayers are considered “traveling away from home” if their duties require them to be away from home substantially longer than an ordinary day’s work and they need to sleep or rest to meet the demands of their work. The actual cost of meals and incidental expenses may be deducted or the taxpayer may use a standard meal allowance and reduced record keeping requirements. Regardless of the method used, meal deductions are generally limited to 50 percent as stated earlier. Only actual costs for lodging may be claimed as an expense and receipts must be kept for documentation. ...
`Instruct: Given a web search query, retrieve relevant passages that answer the query Query: Business Expense - Car Insurance Deductible For Accident That Occurred During a Business Trip`	As a general rule, you must choose between a mileage deduction or an actual expenses deduction. The idea is that the mileage deduction is supposed to cover all costs of using the car. Exceptions include parking fees and tolls, which can be deducted separately under either method. You explicitly cannot deduct insurance costs if you claim a mileage deduction. Separately, you probably won't be able to deduct the deductible for your car as a casualty loss. You first subtract $100 from the deductible and then divide it by your Adjusted Gross Income (AGI) from your tax return. If your deductible is over 10% of your AGI, you can deduct it. Note that even with a $1500 deductible, you won't be able to deduct anything if you made more than $14,000 for the year. For most people, the insurance deductible just isn't large enough relative to income to be tax deductible. Source
`Instruct: Given a web search query, retrieve relevant passages that answer the query Query: Starting a new online business`	Most US states have rules that go something like this: You will almost certainly have to pay some registration fees, as noted above. Depending on how you organize, you may or may not need to file a separate tax return for the business. (If you're sole proprietor for tax purposes, then you file on Schedule C on your personal Form 1040.) Whether or not you pay taxes depends on whether you have net income. It's possible that some losses might also be deductible. (Note that you may have to file a return even if you don't have net income - Filing and needing to pay are not the same since your return may indicate no tax due.) In addition, at the state level, you may have to pay additional fees or taxes beyond income tax depending on what you sell and how you sell it. (Sales tax, for example, might come into play as might franchise taxes.) You'll need to check your own state law for that. As always, it could be wise to get professional tax and accounting advice that's tailored to your si...

Loss: zero-neuron.src.embedding.sparse_loss.SparseLoss

Training Hyperparameters

Non-Default Hyperparameters

per_device_eval_batch_size: 16
learning_rate: 0.0005
num_train_epochs: 2
lr_scheduler_type: cosine
warmup_ratio: 0.01
save_safetensors: False
bf16: True
remove_unused_columns: False
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: no
prediction_loss_only: True
per_device_train_batch_size: 8
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 0.0005
weight_decay: 0.0
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: cosine
lr_scheduler_kwargs: {}
warmup_ratio: 0.01
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: False
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: False
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: None
hub_always_push: False
hub_revision: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Click to expand

Epoch	Step	Training Loss
0.0056	10	1.1694
0.0113	20	1.2809
0.0169	30	1.2538
0.0226	40	1.2237
0.0282	50	1.1809
0.0339	60	1.1602
0.0395	70	1.2008
0.0452	80	1.1064
0.0508	90	1.0857
0.0565	100	1.0553
0.0621	110	1.0513
0.0678	120	0.9236
0.0734	130	0.8998
0.0791	140	0.8509
0.0847	150	0.7769
0.0903	160	0.7268
0.0960	170	0.7287
0.1016	180	0.6437
0.1073	190	0.6653
0.1129	200	0.5888
0.1186	210	0.6097
0.1242	220	0.6939
0.1299	230	0.5969
0.1355	240	0.5333
0.1412	250	0.5143
0.1468	260	0.6152
0.1525	270	0.4779
0.1581	280	0.5182
0.1637	290	0.5724
0.1694	300	0.5073
0.1750	310	0.4924
0.1807	320	0.5219
0.1863	330	0.5621
0.1920	340	0.4535
0.1976	350	0.4818
0.2033	360	0.4773
0.2089	370	0.4948
0.2146	380	0.4277
0.2202	390	0.5043
0.2259	400	0.5746
0.2315	410	0.4762
0.2372	420	0.4432
0.2428	430	0.4771
0.2484	440	0.5298
0.2541	450	0.4352
0.2597	460	0.5714
0.2654	470	0.508
0.2710	480	0.5215
0.2767	490	0.5096
0.2823	500	0.4598
0.2880	510	0.5843
0.2936	520	0.5581
0.2993	530	0.4686
0.3049	540	0.4956
0.3106	550	0.4209
0.3162	560	0.4181
0.3219	570	0.4847
0.3275	580	0.5193
0.3331	590	0.4235
0.3388	600	0.4626
0.3444	610	0.4309
0.3501	620	0.451
0.3557	630	0.4742
0.3614	640	0.4892
0.3670	650	0.4478
0.3727	660	0.4461
0.3783	670	0.5197
0.3840	680	0.4692
0.3896	690	0.4272
0.3953	700	0.4196
0.4009	710	0.4737
0.4065	720	0.4015
0.4122	730	0.4786
0.4178	740	0.3968
0.4235	750	0.4499
0.4291	760	0.478
0.4348	770	0.4003
0.4404	780	0.4679
0.4461	790	0.4129
0.4517	800	0.452
0.4574	810	0.4238
0.4630	820	0.4761
0.4687	830	0.4324
0.4743	840	0.4535
0.4800	850	0.4914
0.4856	860	0.5368
0.4912	870	0.4106
0.4969	880	0.419
0.5025	890	0.3884
0.5082	900	0.4833
0.5138	910	0.4295
0.5195	920	0.3673
0.5251	930	0.4245
0.5308	940	0.4636
0.5364	950	0.3897
0.5421	960	0.4342
0.5477	970	0.442
0.5534	980	0.4443
0.5590	990	0.3737
0.5647	1000	0.441
0.5703	1010	0.4247
0.5759	1020	0.4583
0.5816	1030	0.4077
0.5872	1040	0.5236
0.5929	1050	0.4307
0.5985	1060	0.5054
0.6042	1070	0.4787
0.6098	1080	0.4521
0.6155	1090	0.4011
0.6211	1100	0.3864
0.6268	1110	0.4191
0.6324	1120	0.436
0.6381	1130	0.4469
0.6437	1140	0.4416
0.6494	1150	0.4475
0.6550	1160	0.3857
0.6606	1170	0.3571
0.6663	1180	0.441
0.6719	1190	0.4144
0.6776	1200	0.4108
0.6832	1210	0.4051
0.6889	1220	0.489
0.6945	1230	0.3881
0.7002	1240	0.4971
0.7058	1250	0.415
0.7115	1260	0.4048
0.7171	1270	0.3805
0.7228	1280	0.3869
0.7284	1290	0.3804
0.7340	1300	0.4141
0.7397	1310	0.4223
0.7453	1320	0.3836
0.7510	1330	0.4012
0.7566	1340	0.4725
0.7623	1350	0.3946
0.7679	1360	0.4424
0.7736	1370	0.4256
0.7792	1380	0.4381
0.7849	1390	0.3634
0.7905	1400	0.3568
0.7962	1410	0.4158
0.8018	1420	0.3982
0.8075	1430	0.4734
0.8131	1440	0.3787
0.8187	1450	0.4492
0.8244	1460	0.4504
0.8300	1470	0.4125
0.8357	1480	0.4059
0.8413	1490	0.419
0.8470	1500	0.4269
0.8526	1510	0.5586
0.8583	1520	0.4664
0.8639	1530	0.5185
0.8696	1540	0.422
0.8752	1550	0.5141
0.8809	1560	0.4576
0.8865	1570	0.372
0.8922	1580	0.4194
0.8978	1590	0.4074
0.9034	1600	0.3894
0.9091	1610	0.4172
0.9147	1620	0.4274
0.9204	1630	0.4013
0.9260	1640	0.4072
0.9317	1650	0.3616
0.9373	1660	0.3485
0.9430	1670	0.4478
0.9486	1680	0.4543
0.9543	1690	0.4229
0.9599	1700	0.4186
0.9656	1710	0.378
0.9712	1720	0.3753
0.9768	1730	0.4575
0.9825	1740	0.4291
0.9881	1750	0.4288
0.9938	1760	0.3678
0.9994	1770	0.5298
1.0051	1780	0.3926
1.0107	1790	0.3799
1.0164	1800	0.4288
1.0220	1810	0.4323
1.0277	1820	0.4371
1.0333	1830	0.4652
1.0390	1840	0.3565
1.0446	1850	0.4567
1.0503	1860	0.3947
1.0559	1870	0.3868
1.0615	1880	0.4143
1.0672	1890	0.482
1.0728	1900	0.3763
1.0785	1910	0.3795
1.0841	1920	0.4413
1.0898	1930	0.4761
1.0954	1940	0.3907
1.1011	1950	0.4066
1.1067	1960	0.3905
1.1124	1970	0.3944
1.1180	1980	0.4022
1.1237	1990	0.398
1.1293	2000	0.3473
1.1350	2010	0.4357
1.1406	2020	0.3823
1.1462	2030	0.3628
1.1519	2040	0.403
1.1575	2050	0.3965
1.1632	2060	0.3837
1.1688	2070	0.5012
1.1745	2080	0.3959
1.1801	2090	0.3661
1.1858	2100	0.4603
1.1914	2110	0.4607
1.1971	2120	0.4241
1.2027	2130	0.5183
1.2084	2140	0.3533
1.2140	2150	0.3877
1.2196	2160	0.4298
1.2253	2170	0.4228
1.2309	2180	0.4131
1.2366	2190	0.4034
1.2422	2200	0.3834
1.2479	2210	0.4183
1.2535	2220	0.5475
1.2592	2230	0.4755
1.2648	2240	0.4478
1.2705	2250	0.3763
1.2761	2260	0.4493
1.2818	2270	0.4001
1.2874	2280	0.3765
1.2931	2290	0.3379
1.2987	2300	0.337
1.3043	2310	0.4143
1.3100	2320	0.4794
1.3156	2330	0.4004
1.3213	2340	0.3674
1.3269	2350	0.3963
1.3326	2360	0.3896
1.3382	2370	0.5062
1.3439	2380	0.4114
1.3495	2390	0.3955
1.3552	2400	0.4682
1.3608	2410	0.3551
1.3665	2420	0.3536
1.3721	2430	0.3784
1.3778	2440	0.3456
1.3834	2450	0.4273
1.3890	2460	0.4005
1.3947	2470	0.3957
1.4003	2480	0.3371
1.4060	2490	0.3451
1.4116	2500	0.4735
1.4173	2510	0.4013
1.4229	2520	0.3751
1.4286	2530	0.365
1.4342	2540	0.3548
1.4399	2550	0.4227
1.4455	2560	0.3626
1.4512	2570	0.404
1.4568	2580	0.4055
1.4625	2590	0.4513
1.4681	2600	0.4147
1.4737	2610	0.3623
1.4794	2620	0.404
1.4850	2630	0.4
1.4907	2640	0.3854
1.4963	2650	0.4082
1.5020	2660	0.3502
1.5076	2670	0.4022
1.5133	2680	0.4479
1.5189	2690	0.3456
1.5246	2700	0.3992
1.5302	2710	0.4143
1.5359	2720	0.3925
1.5415	2730	0.366
1.5471	2740	0.4254
1.5528	2750	0.4337
1.5584	2760	0.471
1.5641	2770	0.4201
1.5697	2780	0.4357
1.5754	2790	0.4289
1.5810	2800	0.4287
1.5867	2810	0.4349
1.5923	2820	0.4551
1.5980	2830	0.3562
1.6036	2840	0.4925
1.6093	2850	0.4104
1.6149	2860	0.4691
1.6206	2870	0.383
1.6262	2880	0.3612
1.6318	2890	0.4584
1.6375	2900	0.3828
1.6431	2910	0.3784
1.6488	2920	0.4148
1.6544	2930	0.4535
1.6601	2940	0.3523
1.6657	2950	0.3501
1.6714	2960	0.3703
1.6770	2970	0.388
1.6827	2980	0.3846
1.6883	2990	0.4212
1.6940	3000	0.4192
1.6996	3010	0.4265
1.7053	3020	0.4385
1.7109	3030	0.4197
1.7165	3040	0.3488
1.7222	3050	0.3666
1.7278	3060	0.3909
1.7335	3070	0.5085
1.7391	3080	0.3495
1.7448	3090	0.4198
1.7504	3100	0.3647
1.7561	3110	0.3873
1.7617	3120	0.4038
1.7674	3130	0.4471
1.7730	3140	0.4078
1.7787	3150	0.3823
1.7843	3160	0.4852
1.7899	3170	0.3891
1.7956	3180	0.4334
1.8012	3190	0.3836
1.8069	3200	0.4
1.8125	3210	0.4126
1.8182	3220	0.3767
1.8238	3230	0.4085
1.8295	3240	0.3919
1.8351	3250	0.358
1.8408	3260	0.3709
1.8464	3270	0.4131
1.8521	3280	0.4082
1.8577	3290	0.4547
1.8634	3300	0.4317
1.8690	3310	0.3981
1.8746	3320	0.4585
1.8803	3330	0.3698
1.8859	3340	0.3662
1.8916	3350	0.3955
1.8972	3360	0.4387
1.9029	3370	0.5001
1.9085	3380	0.3708
1.9142	3390	0.4448
1.9198	3400	0.3632
1.9255	3410	0.4589
1.9311	3420	0.4085
1.9368	3430	0.3993
1.9424	3440	0.4598
1.9481	3450	0.4019
1.9537	3460	0.4179
1.9593	3470	0.3804
1.9650	3480	0.4229
1.9706	3490	0.3933
1.9763	3500	0.4217
1.9819	3510	0.4182
1.9876	3520	0.5265
1.9932	3530	0.403
1.9989	3540	0.3758

Framework Versions

Python: 3.10.16
Sentence Transformers: 5.1.1
Transformers: 4.55.4
PyTorch: 2.6.0+cu124
Accelerate: 1.8.0.dev0
Datasets: 3.2.0
Tokenizers: 0.21.4

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}
}