Want to learn more? I’m launching a 6-week live BootCamp for AI Builders. Learn more: …
[ad_2]
source
Want to learn more? I’m launching a 6-week live BootCamp for AI Builders. Learn more: …
[ad_2]
source
Lorem ipsum dolor sit amet, consectetur.
UPDATE: Someone pointed out that the fine-tuned model here is overfitting, so I created an improved example that uses transfer learning: https://youtu.be/4QHg8Ix8WWQ
👉More on LLMs: https://www.youtube.com/playlist?list=PLz-ep5RbHosU2hnz5ejezwaYpdMutMVB0
—
References
[1] Deeplearning.ai Finetuning Large Langauge Models Short Course: https://www.deeplearning.ai/short-courses/finetuning-large-language-models/
[2] arXiv:2005.14165 [cs.CL] (GPT-3 Paper)
[3] arXiv:2303.18223 [cs.CL] (Survey of LLMs)
[4] arXiv:2203.02155 [cs.CL] (InstructGPT paper)
[5] PEFT: Parameter-Efficient Fine-Tuning of Billion-Scale Models on Low-Resource Hardware: https://huggingface.co/blog/peft
[6] arXiv:2106.09685 [cs.CL] (LoRA paper)
[7] Original dataset source — Andrew L. Maas, Raymond E. Daly, Peter T. Pham, Dan Huang, Andrew Y. Ng, and Christopher Potts. 2011. Learning Word Vectors for Sentiment Analysis. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 142–150, Portland, Oregon, USA. Association for Computational Linguistics.
Nice job, efficient , straight forward, enough detail for learning big picture without confusion.
Can you fine tuning a fine tuned models from huggingface?
Indepth overview of fine tuning!
Bro you are the best instructor
very explicit explanation. Thanks!
This video series is underrated. Loved it, thank you!
Very good explain about fine tune, thanks Shaw
Teacher, can you tune it for me
thank you sooo much for this content, it's so helpful and clear!!!
if i don't use LoRa when fine-tuning and instead just specify `Trainer(model=AutoModelForSequenceClassification.from_pretrained(
model_checkpoint, num_labels=2)` (which is what huggingface does in most of its documentation), what type of parameter training is that performing? retraining all of the parameters?
Thank you, is a nice video and you have a clear explanation, actually I try to do this with GPT Neo model (EleutherAI/gpt-neo-1.3B) but when I do training, the Training Loss always have no log values and Validation Loss always NaN (when do it with BERT or distilbert, is run perfectly), Do you have any suggestions or reading resources to fix this?
Hey, It was good but did your Model also take a lot of time to get fine-tuned while you were Pluging everything to the Trainer Class as for me it's taking nearly i lost the time it is taking but 10 epochs are getting trained for every 0.05 it/s.
Why is truncation side set to the left? What is the difference between choosing "right" or "left"? I'm asking in a general sense, not just for the example shown here. Is there anyone that can provide some intuition or good reading references?
You're a fantastic communicator – this was very helpful. I would love to see more walkthroughs like this that have a good balance of theory, math and python.
Hands down one of the most best explanations on youtube keep it up homie
Hey YouTube, I really liked this kind of machine learning and fine tuning topics. Please recommend me more of these.
Thank you for the great content.
great video.
Why has dropout parameter to config LoRA? What drop in formular?
Very informative video. Thanks for sharing
Loving the info! Do you have a video on self-supervised training? I want to train a llm to write in my style.
Dont fall for these stupid ideas – this is good for Youtube video – you will never be able to train it in a level that someone will pay "MONEY" for your trained model.
Hey YouTube algorithm , I loved this video . suggest me more of them
I loved the video
I needed to know how parameter efficient finetuning works to finetune a voice encoder for emotion detection task. This video helped me a lot. I used LoRA for it. Thanks ❤
Very amazing video!!! I have one question: when I use your code to fine-tune the model with my own dataset, but since my dataset is too large it leads to memory error (not gpu memory) when I read the dataset, what should I do to avoid this issue? Can I read and fine-tune in a small batch?
I'm wanting to use an LLM for sentiment analysis and textual content classification and require a very specific JSON output structure for further processing and storage… would this be possible via fine-tuning? Could you (or anyone) perhaps point me in the right direction?
Thanks for these great videos. I really love the fact that you focus on building an intuitive understanding as opposed to throwing jargons. Could you please start a langchain series?
but during back propogation,,, each value in A is dependent on EACH value of B so again there are A*B dimensionality to be impoved or you are ignoring other wights apart from diogonal eleemnts
Thanks for the well defined video because it helped me prepare my proposal related to this topic.
this video helpful using text, hoping you can have a sample of finetuning using images
Video volume is so low, compared to most YT videos
ШАПКУ СНИМИ!
I cant find code in the git link provide, can anyone please send me the code please
Finally something that I can grok!!!! Fantastic tutorial!
Excellent way of teaching. Keep doing this kind of good work.