Sabitlenmiş Tweet
Telecom Customer Churn.
An end to end MLOps Projects.
Built using
MLflow
Airflow
DVC
Streamlit
Fastapi
AWS
Github actions
Docker
All the updates and down below.
Rishav@anandrishv
i've grown a lot
English
Rishav
3.2K posts
Rishav
@anandrishv
Building end-to-end Machine Learning Systems
Katılım Mart 2023
441 Takip Edilen206 Takipçiler
went shopping with her later. very good day overall, felt so good after a long time
ShaRPeyE@sharpeye_wnl
mandatory monday date
English
@krishdotdev i don't find this useful cause i like things simple which runs my code and don't just make my eye amazed.
English
@ThedatagGuy that's a purposeful time utilisation , better than tweeting and replying !
English
Don't know why I get obsessed with understanding small small details in every topic
It's good for some but it definitely takes a lot of time
Problem is those can't be exposed to someone until unless they are well versed in those topics
I should focus on what is necessary from here
English
@pranavcodes_ i used to youtube when i had to watch something, now they make us watch anything
English
Day 122 🍀
- Woke up at 8:00am
- Completed one unit of Waves and Optics
Purnima Vats@PurnimaaVats
Day 121 🍀 - Woke up at 8:30am - Studied waves and optics - Gave an online assessment
English
After spending 5 days on model training, data cleaning, preprocessing,evaluation,testing. as backened and uses a button to predict Churned/not churned.
Feels machine learning is 10% and 90% engineering about how to use that prediction and make it reach to customer and get result
English
@anandrishv 😭 I'm the only one working in this project
And my professor is not picking the call
Anyway I used another api with different vpn
English
@anandrishv Because it's a small dataset, it took me only ~6min
> 20 epochs
> batch size of 2
> 5k tokens in the dataset (split into train/val)
> ~17s per epoch
English
[ML Grind]
Yesterday I took the day to work on the model training of the GPT-like model. I built the tokenization/embedding layers, the multi-head attention mechanism, added the transformer blocks to the GPTModel, and trained it on input text of 5k tokens (not big but useful for learning purposes).
TK • 木下@wordsofteekay
Continuing my ML progress > LLM from scratch: worked on this all day (built a self-attention and multi-head attention mechanism) > Finished the monitoring system this week > AI Engineering: continue the book — I'm currently working on an AI agent product and I need to learn more about this one > Got a mentor at work: he shared many papers and resources I should read (tons of work to do!) > ML Bootcamp: working on the first project with my pair — first part (EDA) is done. Now I need to move to the model training phase
English
Airflow schedules the projects and runs in every 15min/hour/day.
No need to run the project manually, it automates and orchestrates the project, each step is executed after each one.
MLFlow tracks the performance, params, evaluation metrics of project store. Logged in
Rishav@anandrishv
Successfully Ran the Airflow DAG. No Errors. each steps executed smoothly. As scheduled it's running the project in every 15 min. It ran the project, gave the output - Recall : 0.96. MLFlow tracking the project assigned airflow in it.
English
Rishav retweetledi
POV: everyone’s got a macbook
and you walk in with a gaming laptop 😂
English
