[HN Gopher] Learnings from fine-tuning LLM on my Telegram messages ___________________________________________________________________ Learnings from fine-tuning LLM on my Telegram messages Author : furiousteabag Score : 122 points Date : 2023-11-27 17:09 UTC (5 hours ago) (HTM) web link (asmirnov.xyz) (TXT) w3m dump (asmirnov.xyz) | NoraCodes wrote: | A meta-comment, but, what is the difference between "learnings" | and "lessons"? Why use the former when we have the latter? | bigdict wrote: | learnings = lessons learned | Jolter wrote: | Lessons may be given, but are not necessarily learned. | c0pium wrote: | Gotta earn those fat management consultant fees somehow. I'm | sure there's a whole team at McKinsey doing nothing but | inventing new ways to say the same things. | fl7305 wrote: | In Swedish, there's a commonly used word "lardomar" which is | a direct match for "learnings". | | But where the Swedish word sounds natural in that language, | "learnings" just sounds wrong in English, even though it | apparently is technically correct. | furyofantares wrote: | Learnings implies a report of your own experience; lessons | implies something prepared as teaching material for the | audience. (In the context of the title sentence anyway.) | xanderlewis wrote: | 'Lessons' to me also seems to carry a sense of regret, as in | 'things (we) got wrong'. 'Learnings' is a more obscure word | that I would take to mean something more neutral: literally | 'things (I've) learnt'. | kagol wrote: | Perhaps "findings" over "learnings", based on your | description? | klooney wrote: | I've always associated it with Indian English, possibly it's a | dialect thing that's spread from that community. | xanderlewis wrote: | Maybe it's Kazakh. https://en.m.wikipedia.org/wiki/Borat | | ;-) | swatcoder wrote: | https://en.m.wiktionary.org/wiki/learnings | | Beyond what's noted there (contemporary business jargon), | English is diffused across the globe and has many regional | variations that are different than class-signalling/formal | American and British usage. As we all encounter each other | online, it's not always worth over-analyzing word choice when | you can understand the intent. | bee_rider wrote: | I think when you ask what the difference between two phrases | is, people will really dig down to try and find a difference. | | IMO in this context it is basically shorthand for "things I | learned/lessons learned while tuning LLM...," and either would | be fine. It is sort of an informal list of stuff the author | learned. | | In my experience (nothing special, just another native speaker) | "lessons from <event>" is the more typical American (at least) | English phrase. But it is sort of close to "Lessons on." | "Lessons on" would imply more refined material that is more | narrowly focused on teaching. So I wonder if the author decided | they just didn't want to worry about any confusion, or the | possibility that they might misuse a phrase. | AlexCoventry wrote: | I think it's new. I've only heard it in the last few years. | amccollum wrote: | This usage of "learnings", while certainly more common in | "business jargon" today, was used by Shakespeare: | | https://www.opensourceshakespeare.org/views/plays/play_view.... | nescioquid wrote: | Some words in Shakespeare have different meanings today or | have simply left standard usage. I don't think the presence | of a word in Shakespeare means it is de facto good style to | use today. | | From a correctness stand-point, I think a descriptionist | would be satisfied with an attested usage, especially from | such a source. From a style point of view, I still find | myself feeling embarrassed for the author when I encounter | this usage (which is my own problem). | catlover76 wrote: | I assumed the author was a non-native English speaker | haltist wrote: | Great example of immortal digital avatars. This is just a simple | personal avatar but it is possible to make technological gods | with the same techniques. All that's needed is scale and $80B. | u385639 wrote: | Great post. I wonder how much this can improve if you RAG-ify a | diverse set of contextual data, for example calendar, meals, | recent conversations from the real world, etc. | | It's also interesting that blia was translated to 'damn'. :) | furiousteabag wrote: | I think incorporating knowledge from other apps is a good next | step because the model definitely lacks the context of what is | going on right now. The nature of instant messaging is that | most of the messages are about what is happening right now or | what will happen in the near future, so past communication | history does not help much. | goda90 wrote: | We're probably quite some time off from the bio-mimetic android | part, but we're feeling closer and closer to the AI replacement | avatar from the Black Mirror episode "Be Right Back"[0] | | [0]https://en.wikipedia.org/wiki/Be_Right_Back | thefourthchime wrote: | This part caught my eye: | | "Using a half-precision FSDP full shard with a 1024 sequence | length and a micro batch size of 2 required 63GB of VRAM on each | of the eight A100 80 GB GPUs. The training, lasting three epochs, | took just 20 minutes. The total cost for the VM was $8.88 per | hour, resulting in $3, not including the time for experiments and | bug fixes." | | I wondered where you could rent cycles on a machine like that, a | quick Google found that p4d.24xlarge on AWS is available, while | the on-demand cost is $20.1755 per hour, the Spot is only $8.99 | (I guess it's gone up?) | | Cool to know I could fine-tune for only ~$3. | furiousteabag wrote: | I've been using vast.ai for a very long time. It is like a GPU | marketplace, where people rent and lease GPUs. There are a lot | of VMs with 4090, and beasts like 8xA100 80GB are also | available from time to time. | skerit wrote: | I've used vast.ai to do some fine-tuning just a few days ago. | It is indeed pretty great, though some servers fail to start | up properly, or have some weird performance issues. I also | wish they had more templates to try. | siquick wrote: | Excuse the ignorance but are you using these instances to fine | tune a "fresh install" of a model, and then when you've | finished fine tuning it do you download the whole model from | the instance for use somewhere else? | jsight wrote: | I think Tensordock and vast.ai are cheaper than AWS. Lambda | labs can be as well, but they seem to only have reserved | instances now. | cosmojg wrote: | runpod.io is another good-and-cheap option | lloydatkinson wrote: | "Learnings" is such a horrible word | 123sereusername wrote: | "Learnings" While it might be legal, Learnings is a terrible | abuse of the English language. | ryanklee wrote: | This is a ridiculous, arbitrary judgment that has nothing to do | with anything even remotely related to this post. This type of | pedantry is low-brow and annoying. | aerhardt wrote: | It's also plainly wrong, because "learnings" is perfectly | commonplace. | amccollum wrote: | Take it up with Shakespeare? | | https://www.opensourceshakespeare.org/views/plays/play_view.... | sfink wrote: | I'm a native English speaker from the US, and a pedant who | hates "ask" as a noun, "workshop" as a verb, and "performant" | as a word. But I don't get the hate for "learnings" here. | What's wrong with it? "Lessons" connotes negativity, "stuff I | learned" doesn't naturally fit into many sentences, and "useful | information gleaned" can be shoved right back up the tightly | puckered ass it came out of. | | What's the problem? That title is exactly the way I would have | written it. | kagol wrote: | I always thought of "learning" as an uncountable noun. | korhojoa wrote: | Out of curiosity, what's your take on how to write "this item | requires repair"? | | "It needs repaired" is something I've seen, which to me is | confusing, because it seems like "to be" is missing. When did | "needs" run away from the words it's been associated with | before? | swatcoder wrote: | They wrote this for you, I think: | | https://ygdp.yale.edu/phenomena/needs-washed | esafak wrote: | So you're saying "needs" is not doing the needful. | pweezy wrote: | This is a regionalism in parts of the US, which I've seen | described as Pittsburgh and its surroundings. | | I come across it often and struggle with cognitive | dissonance every time - I know of the regionalism but it | feels so strongly like a glaring grammatical error. | | I see/hear the specific phrase "needs fixed" most often. | gwern wrote: | > My data collator ensures that the loss is only calculated based | on someone's response. Predicting who will speak next is | relatively straightforward, and we don't want the model to focus | on learning that. Therefore, parts of the conversation where the | loss is calculated are highlighted in bold. | | If it's so easy, then you don't need to remove it. The model will | solve it easily and focus on everything else. At best, you save | some parameters and compute, at worst, you are damaging its | ability to learn important things like conversational skills or | modeling people. When it comes to LLMs, more is more, and trying | to hand-engineer the dataset or think _for_ the LLM can backfire | in very subtle and difficult to diagnose ways. | | > Ok, it is capable of forming coherent sentences. The most | noticeable problem is its lack of awareness regarding the context | of the conversations which leads to bland and generic replies. | The messages lacked any distinct style, feeling quite basic... > | > Conversations have become more interesting and engaging, | although there's still a risk of losing context. Russian language | performance has improved, but errors still occur. I believe that | before fine-tuning for a specific task with limited data, like | mine, it would be beneficial to first fine-tune the model | unsupervised on a large corpus of Russian texts. Additionally, | incorporating common conversation partners' names as separate | tokens might enhance the quality. I wouldn't say it has turned | out to be significantly better than LoRA. It might be more | effective to focus solely on a single person and calculate the | loss based only on my responses (or someone else's), instead of | trying to learn about each and every conversational partner. ___________________________________________________________________ (page generated 2023-11-27 23:00 UTC)