README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:1668
  - loss:LoggableMNRL
widget:
  - source_sentence: >-
      t started. [5]It can be dangerous to delay turning yourself into a
      company, because one or more of the founders might decide to split off and
      start another company doing the same thing. This does happen. So when you
      set up the company, as well as as apportioning the stock, you should get
      all the founders to sign something agreeing that everyone's ideas belong
      to this company, and that this company is going to be everyone's only
      job.[If this were a movie, ominous music would begin here.]While you're at
      it, you should ask what else they've signed. One of the worst things that
      can happen to a startup is to run into intellectual property problems. We
      did, and it came closer to killing us than any competitor ever did. As we
      were in the middle of getting bought, we discovered that one of our people
      had, early on, been bound by an agreement that said all his ideas belonged
      to the giant company that was paying for him to go to grad school. In
      theory, that could have meant someone else owned big chunks of our
      software. So the acquisition came to a screeching halt while we tried to
      sort this out. The problem was, since we'd been about to be acquired, we'd
      allowed ourselves to run low on cash
    sentences:
      - >-
        what we should expect in the future is more of the same. Indeed, we
        should expect both the number and wealth of founders to grow, because
        every decade it gets easier to start a startup. Part of the reason it's
        getting easier to start a startup is social. Society is (re)assimilating
        the concept. If you start one now, your parents won't freak out the way
        they would have a generation ago, and knowledge about how to do it is
        much more widespread. But the main reason it's easier to start a startup
        now is that it's cheaper. Technology has driven down the cost of both
        building products and acquiring customers. The decreasing cost of
        starting a startup has in turn changed the balance of power between
        founders and investors. Back when starting a startup meant building a
        factory, you needed investors' permission to do it at all. But now
        investors need founders more than founders need investors, and that,
        combined with the increasing amount of venture capital available, has
        driven up valuations. [8]So the decreasing cost of starting a startup
        increases the number of rich people in two ways: it means that more
        people start them, and that those who do can raise money on better
        terms. But there'
      - >-
        e a company when, as sometimes happens, its whole market dies, just as
        property managers can't save you from the building burning down. But a
        company that managed a large enough number of companies could say to all
        its clients: we'll combine the revenues from all your companies, and pay
        you your proportionate share. If such management companies existed,
        they'd offer the maximum of freedom and security. Someone would run your
        company for you, and you'd be protected even if it happened to die.
        Let's think about how such a management company might be organized. The
        simplest way would be to have a new kind of stock representing the total
        pool of companies they were managing. When you signed up, you'd trade
        your company's stock for shares of this pool, in proportion to an
        estimate of your company's value that you'd both agreed upon. Then you'd
        automatically get your share of the returns of the whole pool. The catch
        is that because this kind of trade would be hard to undo, you couldn't
        switch management companies. But there's a way they could fix that:
        suppose all the company management companies got together and agreed to
        allow their clients to exchange shares in all their pools. Then y
      - >-
        t started. [5]It can be dangerous to delay turning yourself into a
        company, because one or more of the founders might decide to split off
        and start another company doing the same thing. This does happen. So
        when you set up the company, as well as as apportioning the stock, you
        should get all the founders to sign something agreeing that everyone's
        ideas belong to this company, and that this company is going to be
        everyone's only job.[If this were a movie, ominous music would begin
        here.]While you're at it, you should ask what else they've signed. One
        of the worst things that can happen to a startup is to run into
        intellectual property problems. We did, and it came closer to killing us
        than any competitor ever did. As we were in the middle of getting
        bought, we discovered that one of our people had, early on, been bound
        by an agreement that said all his ideas belonged to the giant company
        that was paying for him to go to grad school. In theory, that could have
        meant someone else owned big chunks of our software. So the acquisition
        came to a screeching halt while we tried to sort this out. The problem
        was, since we'd been about to be acquired, we'd allowed ourselves to run
        low on cash
  - source_sentence: ' happen fast. For example, Y Combinator has now invested in 80 startups, 57 of which are still alive. (The rest have died or merged or been acquired.) When you''re trying to advise 57 startups, it turns out you have to have a stateless algorithm. You can''t have ulterior motives when you have 57 things going on at once, because you can''t remember them. So our rule is just to do whatever''s best for the founders. Not because we''re particularly benevolent, but because it''s the only algorithm that works on that scale. When you write something telling people to be good, you seem to be claiming to be good yourself. So I want to say explicitly that I am not a particularly good person. When I was a kid I was firmly in the camp of bad. The way adults used the word good, it seemed to be synonymous with quiet, so I grew up very suspicious of it. You know how there are some people whose names come up in conversation and everyone says "He''s such a great guy?" People never say that about me. The best I get is "he means well." I am not claiming to be good. At best I speak good as a second language. So I''m not suggesting you be good in the usual sanctimonious way. I''m suggesting it because it works.'
    sentences:
      - ' happen fast. For example, Y Combinator has now invested in 80 startups, 57 of which are still alive. (The rest have died or merged or been acquired.) When you''re trying to advise 57 startups, it turns out you have to have a stateless algorithm. You can''t have ulterior motives when you have 57 things going on at once, because you can''t remember them. So our rule is just to do whatever''s best for the founders. Not because we''re particularly benevolent, but because it''s the only algorithm that works on that scale. When you write something telling people to be good, you seem to be claiming to be good yourself. So I want to say explicitly that I am not a particularly good person. When I was a kid I was firmly in the camp of bad. The way adults used the word good, it seemed to be synonymous with quiet, so I grew up very suspicious of it. You know how there are some people whose names come up in conversation and everyone says "He''s such a great guy?" People never say that about me. The best I get is "he means well." I am not claiming to be good. At best I speak good as a second language. So I''m not suggesting you be good in the usual sanctimonious way. I''m suggesting it because it works.'
      - >-
        hether it's net good or bad, but my guess is bad.[7] One of the reasons
        people work so hard on startups is that startups can fail, and when they
        do, that failure tends to be both decisive and conspicuous.[8] It's ok
        to work on something to make a lot of money. You need to solve the money
        problem somehow, and there's nothing wrong with doing that efficiently
        by trying to make a lot at once. I suppose it would even be ok to be
        interested in money for its own sake; whatever floats your boat. Just so
        long as you're conscious of your motivations. The thing to avoid is
        unconsciously letting the need for money warp your ideas about what kind
        of work you find most interesting.[9] Many people face this question on
        a smaller scale with individual projects. But it's easier both to
        recognize and to accept a dead end in a single project than to abandon
        some type of work entirely. The more determined you are, the harder it
        gets. Like a Spanish Flu victim, you're fighting your own immune system:
        Instead of giving up, you tell yourself, I should just try harder. And
        who can say you're not right?


        Thanks to Trevor Blackwell, John Carmack, John Collison, Patrick
        Collison, Robert Morris, Geoff Ralsto
      - >-
        ign is a definite skill. It's not just an airy intangible. Things always
        seem intangible when you don't understand them. Electricity seemed an
        airy intangible to most people in 1800. Who knew there was so much to
        know about it? So it is with design. Some people are good at it and some
        people are bad at it, and there's something very tangible they're good
        or bad at. The reason design counts so much in software is probably that
        there are fewer constraints than on physical things. Building physical
        things is expensive and dangerous. The space of possible choices is
        smaller; you tend to have to work as part of a larger group; and you're
        subject to a lot of regulations. You don't have any of that if you and a
        couple friends decide to create a new web-based application. Because
        there's so much scope for design in software, a successful application
        tends to be way more than the sum of its patents. What protects little
        companies from being copied by bigger competitors is not just their
        patents, but the thousand little things the big company will get wrong
        if they try. The second reason patents don't count for much in our world
        is that startups rarely attack big companies head-on, the way R
  - source_sentence: >-
      ng on optimization is counter to the general trend in software development
      for the last several decades. Trying to write the sufficiently smart
      compiler is by definition a mistake. And even if it weren't, compilers are
      the sort of software that's supposed to be created by open source
      projects, not companies. Plus if this works it will deprive all the
      programmers who take pleasure in making multithreaded apps of so much
      amusing complexity. The forum troll I have by now internalized doesn't
      even know where to begin in raising objections to this project. Now that's
      what I call a startup idea.7. Ongoing DiagnosisBut wait, here's another
      that could face even greater resistance: ongoing, automatic medical
      diagnosis. One of my tricks for generating startup ideas is to imagine the
      ways in which we'll seem backward to future generations. And I'm pretty
      sure that to people 50 or 100 years in the future, it will seem barbaric
      that people in our era waited till they had symptoms to be diagnosed with
      conditions like heart disease and cancer. For example, in 2004 Bill
      Clinton found he was feeling short of breath. Doctors discovered that
      several of his arteries were over 90% blocked and 3 days la
    sentences:
      - >-
        lude working unsubscribe links in their mails. And this would be a
        necessity for smaller fry, and for "legitimate" sites that hired
        spammers to promote them. So if auto-retrieving filters became
        widespread, they'd become auto-unsubscribing filters. In this scenario,
        spam would, like OS crashes, viruses, and popups, become one of those
        plagues that only afflict people who don't bother to use the right
        software. Notes[1] Auto-retrieving filters will have to follow
        redirects, and should in some cases (e. g. a page that just says "click
        here") follow more than one level of links. Make sure too that the http
        requests are indistinguishable from those of popular Web browsers,
        including the order and referrer. If the response doesn't come back
        within x amount of time, default to some fairly high spam probability.
        Instead of making n constant, it might be a good idea to make it a
        function of the number of spams that have been seen mentioning the site.
        This would add a further level of protection against abuse and
        accidents.[2] The original version of this article used the term
        "whitelist" instead of "blacklist" Though they were to work like
        blacklists, I preferred to call them whitelists be
      - >-
        ng on optimization is counter to the general trend in software
        development for the last several decades. Trying to write the
        sufficiently smart compiler is by definition a mistake. And even if it
        weren't, compilers are the sort of software that's supposed to be
        created by open source projects, not companies. Plus if this works it
        will deprive all the programmers who take pleasure in making
        multithreaded apps of so much amusing complexity. The forum troll I have
        by now internalized doesn't even know where to begin in raising
        objections to this project. Now that's what I call a startup idea.7.
        Ongoing DiagnosisBut wait, here's another that could face even greater
        resistance: ongoing, automatic medical diagnosis. One of my tricks for
        generating startup ideas is to imagine the ways in which we'll seem
        backward to future generations. And I'm pretty sure that to people 50 or
        100 years in the future, it will seem barbaric that people in our era
        waited till they had symptoms to be diagnosed with conditions like heart
        disease and cancer. For example, in 2004 Bill Clinton found he was
        feeling short of breath. Doctors discovered that several of his arteries
        were over 90% blocked and 3 days la
      - ' used to amuse himself by breaking into safes containing secret documents. This tradition continues today. When we were in grad school, a hacker friend of mine who spent too much time around MIT had his own lock picking kit. (He now runs a hedge fund, a not unrelated enterprise.)It is sometimes hard to explain to authorities why one would want to do such things. Another friend of mine once got in trouble with the government for breaking into computers. This had only recently been declared a crime, and the FBI found that their usual investigative technique didn''t work. Police investigation apparently begins with a motive. The usual motives are few: drugs, money, sex, revenge. Intellectual curiosity was not one of the motives on the FBI''s list. Indeed, the whole concept seemed foreign to them. Those in authority tend to be annoyed by hackers'' general attitude of disobedience. But that disobedience is a byproduct of the qualities that make them good programmers. They may laugh at the CEO when he talks in generic corporate newspeech, but they also laugh at someone who tells them a certain problem can''t be solved. Suppress one, and you suppress the other. This attitude is sometimes affe'
  - source_sentence: >-
      father. [8]The second component of independent-mindedness, resistance to
      being told what to think, is the most visible of the three. But even this
      is often misunderstood. The big mistake people make about it is to think
      of it as a merely negative quality. The language we use reinforces that
      idea. You're unconventional. You don't care what other people think. But
      it's not just a kind of immunity. In the most independent-minded people,
      the desire not to be told what to think is a positive force. It's not mere
      skepticism, but an active delight in ideas that subvert the conventional
      wisdom, the more counterintuitive the better. Some of the most novel ideas
      seemed at the time almost like practical jokes. Think how often your
      reaction to a novel idea is to laugh. I don't think it's because novel
      ideas are funny per se, but because novelty and humor share a certain kind
      of surprisingness. But while not identical, the two are close enough that
      there is a definite correlation between having a sense of humor and being
      independent-minded � just as there is between being humorless and being
      conventional-minded. [9]I don't think we can significantly increase our
      resistance to being told what to
    sentences:
      - >-
        o think of startup ideas. If you do that, you get bad ones that sound
        dangerously plausible. The best approach is more indirect: if you have
        the right sort of background, good startup ideas will seem obvious to
        you. But even then, not immediately. It takes time to come across
        situations where you notice something missing. And often these gaps
        won't seem to be ideas for companies, just things that would be
        interesting to build. Which is why it's good to have the time and the
        inclination to build things just because they're interesting. Live in
        the future and build what seems interesting. Strange as it sounds,
        that's the real recipe. Notes[1] This form of bad idea has been around
        as long as the web. It was common in the 1990s, except then people who
        had it used to say they were going to create a portal for x instead of a
        social network for x. Structurally the idea is stone soup: you post a
        sign saying "this is the place for people interested in x," and all
        those people show up and you make money from them. What lures founders
        into this sort of idea are statistics about the millions of people who
        might be interested in each type of x. What they forget is that any
        given person might ha
      - >-
        father. [8]The second component of independent-mindedness, resistance to
        being told what to think, is the most visible of the three. But even
        this is often misunderstood. The big mistake people make about it is to
        think of it as a merely negative quality. The language we use reinforces
        that idea. You're unconventional. You don't care what other people
        think. But it's not just a kind of immunity. In the most
        independent-minded people, the desire not to be told what to think is a
        positive force. It's not mere skepticism, but an active delight in ideas
        that subvert the conventional wisdom, the more counterintuitive the
        better. Some of the most novel ideas seemed at the time almost like
        practical jokes. Think how often your reaction to a novel idea is to
        laugh. I don't think it's because novel ideas are funny per se, but
        because novelty and humor share a certain kind of surprisingness. But
        while not identical, the two are close enough that there is a definite
        correlation between having a sense of humor and being independent-minded
        � just as there is between being humorless and being
        conventional-minded. [9]I don't think we can significantly increase our
        resistance to being told what to
      - >-
        ht happen. Well, if you're troubled by uncertainty, I can solve that
        problem for you: if you start a startup, it will probably fail.
        Seriously, though, this is not a bad way to think about the whole
        experience. Hope for the best, but expect the worst. In the worst case,
        it will at least be interesting. In the best case you might get rich. No
        one will blame you if the startup tanks, so long as you made a serious
        effort. There may once have been a time when employers would regard that
        as a mark against you, but they wouldn't now. I asked managers at big
        companies, and they all said they'd prefer to hire someone who'd tried
        to start a startup and failed over someone who'd spent the same time
        working at a big company. Nor will investors hold it against you, as
        long as you didn't fail out of laziness or incurable stupidity. I'm told
        there's a lot of stigma attached to failing in other places—in Europe,
        for example. Not here. In America, companies, like practically
        everything else, are disposable.14. Don't realize what you're
        avoidingOne reason people who've been out in the world for a year or two
        make better founders than people straight from college is that they know
        what they're avoid
  - source_sentence: >-
      ded to take occasional vacations. [5]The only way to find the limit is by
      crossing it. Cultivate a sensitivity to the quality of the work you're
      doing, and then you'll notice if it decreases because you're working too
      hard. Honesty is critical here, in both directions: you have to notice
      when you're being lazy, but also when you're working too hard. And if you
      think there's something admirable about working too hard, get that idea
      out of your head. You're not merely getting worse results, but getting
      them because you're showing off — if not to other people, then to
      yourself. [6]Finding the limit of working hard is a constant, ongoing
      process, not something you do just once. Both the difficulty of the work
      and your ability to do it can vary hour to hour, so you need to be
      constantly judging both how hard you're trying and how well you're doing.
      Trying hard doesn't mean constantly pushing yourself to work, though.
      There may be some people who do, but I think my experience is fairly
      typical, and I only have to push myself occasionally when I'm starting a
      project or when I encounter some sort of check. That's when I'm in danger
      of procrastinating. But once I get rolling, I tend to keep
    sentences:
      - ' is not in itself bad, only when it''s camouflage on insipid form.) Similarly, in painting, a still life of a few carefully observed and solidly modelled objects will tend to be more interesting than a stretch of flashy but mindlessly repetitive painting of, say, a lace collar. In writing it means: say what you mean and say it briefly. It seems strange to have to emphasize simplicity. You''d think simple would be the default. Ornate is more work. But something seems to come over people when they try to be creative. Beginning writers adopt a pompous tone that doesn''t sound anything like the way they speak. Designers trying to be artistic resort to swooshes and curlicues. Painters discover that they''re expressionists. It''s all evasion. Underneath the long words or the "expressive" brush strokes, there is not much going on, and that''s frightening. When you''re forced to be simple, you''re forced to face the real problem. When you can''t deliver ornament, you have to deliver substance. Good design is timeless. In math, every proof is timeless unless it contains a mistake. So what does Hardy mean when he says there is no permanent place for ugly mathematics? He means the same thing Kelly Joh'
      - >-
        same way a biblical literalist is committed to rejecting it. All he's
        committed to is following the evidence wherever it leads. Considering
        yourself a scientist is equivalent to putting a sign in a cupboard
        saying "this cupboard must be kept empty." Yes, strictly speaking,
        you're putting something in the cupboard, but not in the ordinary sense.


        Thanks to Sam Altman, Trevor Blackwell, Paul Buchheit, and Robert Morris
        for reading drafts of this.
      - >-
        ded to take occasional vacations. [5]The only way to find the limit is
        by crossing it. Cultivate a sensitivity to the quality of the work
        you're doing, and then you'll notice if it decreases because you're
        working too hard. Honesty is critical here, in both directions: you have
        to notice when you're being lazy, but also when you're working too hard.
        And if you think there's something admirable about working too hard, get
        that idea out of your head. You're not merely getting worse results, but
        getting them because you're showing off — if not to other people, then
        to yourself. [6]Finding the limit of working hard is a constant, ongoing
        process, not something you do just once. Both the difficulty of the work
        and your ability to do it can vary hour to hour, so you need to be
        constantly judging both how hard you're trying and how well you're
        doing. Trying hard doesn't mean constantly pushing yourself to work,
        though. There may be some people who do, but I think my experience is
        fairly typical, and I only have to push myself occasionally when I'm
        starting a project or when I encounter some sort of check. That's when
        I'm in danger of procrastinating. But once I get rolling, I tend to keep
pipeline_tag: sentence-similarity
library_name: sentence-transformers

SentenceTransformer

This is a sentence-transformers model trained. 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
• 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': False, 'architecture': 'BertModel'})
  (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("sentence_transformers_model_id")
# Run inference
sentences = [
    "ded to take occasional vacations. [5]The only way to find the limit is by crossing it. Cultivate a sensitivity to the quality of the work you're doing, and then you'll notice if it decreases because you're working too hard. Honesty is critical here, in both directions: you have to notice when you're being lazy, but also when you're working too hard. And if you think there's something admirable about working too hard, get that idea out of your head. You're not merely getting worse results, but getting them because you're showing off — if not to other people, then to yourself. [6]Finding the limit of working hard is a constant, ongoing process, not something you do just once. Both the difficulty of the work and your ability to do it can vary hour to hour, so you need to be constantly judging both how hard you're trying and how well you're doing. Trying hard doesn't mean constantly pushing yourself to work, though. There may be some people who do, but I think my experience is fairly typical, and I only have to push myself occasionally when I'm starting a project or when I encounter some sort of check. That's when I'm in danger of procrastinating. But once I get rolling, I tend to keep",
    "ded to take occasional vacations. [5]The only way to find the limit is by crossing it. Cultivate a sensitivity to the quality of the work you're doing, and then you'll notice if it decreases because you're working too hard. Honesty is critical here, in both directions: you have to notice when you're being lazy, but also when you're working too hard. And if you think there's something admirable about working too hard, get that idea out of your head. You're not merely getting worse results, but getting them because you're showing off — if not to other people, then to yourself. [6]Finding the limit of working hard is a constant, ongoing process, not something you do just once. Both the difficulty of the work and your ability to do it can vary hour to hour, so you need to be constantly judging both how hard you're trying and how well you're doing. Trying hard doesn't mean constantly pushing yourself to work, though. There may be some people who do, but I think my experience is fairly typical, and I only have to push myself occasionally when I'm starting a project or when I encounter some sort of check. That's when I'm in danger of procrastinating. But once I get rolling, I tend to keep",
    ' is not in itself bad, only when it\'s camouflage on insipid form.) Similarly, in painting, a still life of a few carefully observed and solidly modelled objects will tend to be more interesting than a stretch of flashy but mindlessly repetitive painting of, say, a lace collar. In writing it means: say what you mean and say it briefly. It seems strange to have to emphasize simplicity. You\'d think simple would be the default. Ornate is more work. But something seems to come over people when they try to be creative. Beginning writers adopt a pompous tone that doesn\'t sound anything like the way they speak. Designers trying to be artistic resort to swooshes and curlicues. Painters discover that they\'re expressionists. It\'s all evasion. Underneath the long words or the "expressive" brush strokes, there is not much going on, and that\'s frightening. When you\'re forced to be simple, you\'re forced to face the real problem. When you can\'t deliver ornament, you have to deliver substance. Good design is timeless. In math, every proof is timeless unless it contains a mistake. So what does Hardy mean when he says there is no permanent place for ugly mathematics? He means the same thing Kelly Joh',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000,  1.0000, -0.1102],
#         [ 1.0000,  1.0000, -0.1102],
#         [-0.1102, -0.1102,  1.0000]])

Training Details

Training Dataset

Unnamed Dataset

• Size: 1,668 training samples
• Columns: sentence_0 and sentence_1
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1
  type	string	string
  details	min: 26 tokens mean: 257.69 tokens max: 345 tokens	min: 26 tokens mean: 257.69 tokens max: 345 tokens

• Samples:

  sentence_0	sentence_1
  ts raison d'etre—is that it offers something otherwise impossible to obtain: a way of measuring that. In many businesses, it just makes more sense for companies to get technology by buying startups rather than developing it in house. You pay more, but there is less risk, and risk is what big companies don't want. It makes the guys developing the technology more accountable, because they only get paid if they build the winner. And you end up with better technology, created faster, because things are made in the innovative atmosphere of startups instead of the bureaucratic atmosphere of big companies. Our startup, Viaweb, was built to be sold. We were open with investors about that from the start. And we were careful to create something that could slot easily into a larger company. That is the pattern for the future.9. CaliforniaThe Bubble was a California phenomenon. When I showed up in Silicon Valley in 1998, I felt like an immigrant from Eastern Europe arriving in America in 1900. Eve...	ts raison d'etre—is that it offers something otherwise impossible to obtain: a way of measuring that. In many businesses, it just makes more sense for companies to get technology by buying startups rather than developing it in house. You pay more, but there is less risk, and risk is what big companies don't want. It makes the guys developing the technology more accountable, because they only get paid if they build the winner. And you end up with better technology, created faster, because things are made in the innovative atmosphere of startups instead of the bureaucratic atmosphere of big companies. Our startup, Viaweb, was built to be sold. We were open with investors about that from the start. And we were careful to create something that could slot easily into a larger company. That is the pattern for the future.9. CaliforniaThe Bubble was a California phenomenon. When I showed up in Silicon Valley in 1998, I felt like an immigrant from Eastern Europe arriving in America in 1900. Eve...
  image rendered with more pixels. One consequence is that some old recipes may have become obsolete. At the very least we have to go back and figure out if they were really recipes for wisdom or intelligence. But the really striking change, as intelligence and wisdom drift apart, is that we may have to decide which we prefer. We may not be able to optimize for both simultaneously. Society seems to have voted for intelligence. We no longer admire the sage—not the way people did two thousand years ago. Now we admire the genius. Because in fact the distinction we began with has a rather brutal converse: just as you can be smart without being very wise, you can be wise without being very smart. That doesn't sound especially admirable. That gets you James Bond, who knows what to do in a lot of situations, but has to rely on Q for the ones involving math. Intelligence and wisdom are obviously not mutually exclusive. In fact, a high average may help support high peaks. But there are reasons t...	image rendered with more pixels. One consequence is that some old recipes may have become obsolete. At the very least we have to go back and figure out if they were really recipes for wisdom or intelligence. But the really striking change, as intelligence and wisdom drift apart, is that we may have to decide which we prefer. We may not be able to optimize for both simultaneously. Society seems to have voted for intelligence. We no longer admire the sage—not the way people did two thousand years ago. Now we admire the genius. Because in fact the distinction we began with has a rather brutal converse: just as you can be smart without being very wise, you can be wise without being very smart. That doesn't sound especially admirable. That gets you James Bond, who knows what to do in a lot of situations, but has to rely on Q for the ones involving math. Intelligence and wisdom are obviously not mutually exclusive. In fact, a high average may help support high peaks. But there are reasons t...
  he mastered a new kind of farming. I've seen the lever of technology grow visibly in my own time. In high school I made money by mowing lawns and scooping ice cream at Baskin-Robbins. This was the only kind of work available at the time. Now high school kids could write software or design web sites. But only some of them will; the rest will still be scooping ice cream. I remember very vividly when in 1985 improved technology made it possible for me to buy a computer of my own. Within months I was using it to make money as a freelance programmer. A few years before, I couldn't have done this. A few years before, there was no such thing as a freelance programmer. But Apple created wealth, in the form of powerful, inexpensive computers, and programmers immediately set to work using it to create more. As this example suggests, the rate at which technology increases our productive capacity is probably exponential, rather than linear. So we should expect to see ever-increasing variation in i...	he mastered a new kind of farming. I've seen the lever of technology grow visibly in my own time. In high school I made money by mowing lawns and scooping ice cream at Baskin-Robbins. This was the only kind of work available at the time. Now high school kids could write software or design web sites. But only some of them will; the rest will still be scooping ice cream. I remember very vividly when in 1985 improved technology made it possible for me to buy a computer of my own. Within months I was using it to make money as a freelance programmer. A few years before, I couldn't have done this. A few years before, there was no such thing as a freelance programmer. But Apple created wealth, in the form of powerful, inexpensive computers, and programmers immediately set to work using it to create more. As this example suggests, the rate at which technology increases our productive capacity is probably exponential, rather than linear. So we should expect to see ever-increasing variation in i...

• Loss: main.LoggableMNRL with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• num_train_epochs: 5
• fp16: True
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 16
• 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: 5e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1
• num_train_epochs: 5
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• 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
• 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}
• 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}
• parallelism_config: None
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch_fused
• optim_args: None
• adafactor: False
• group_by_length: False
• length_column_name: length
• project: huggingface
• trackio_space_id: trackio
• 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: no
• 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: True
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss
4.7619	500	0.1358

Framework Versions

• Python: 3.12.12
• Sentence Transformers: 5.1.2
• Transformers: 4.57.3
• PyTorch: 2.9.0+cu126
• Accelerate: 1.12.0
• Datasets: 4.0.0
• Tokenizers: 0.22.1

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",
}

LoggableMNRL

@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}
}