jndean / LossRider
A plotting tool that outputs Line Rider maps, so you can watch a man on a sled scoot down your loss curves. πΏ
β317Updated 3 months ago
Related projects β
Alternatives and complementary repositories for LossRider
- An interactive HTML pretty-printer for machine learning research in IPython notebooks.β338Updated this week
- A pure NumPy implementation of Mamba.β216Updated 4 months ago
- β139Updated 3 months ago
- The AdEMAMix Optimizer: Better, Faster, Older.β173Updated 2 months ago
- β293Updated 5 months ago
- Transform datasets at scale. Optimize datasets for fast AI model training.β372Updated this week
- TensorHue is a Python library that allows you to visualize tensors right in your console, making understanding and debugging tensor conteβ¦β111Updated last month
- Universal Tensor Operations in Einstein-Inspired Notation for Python.β328Updated last month
- Best practices & guides on how to write distributed pytorch training codeβ291Updated this week
- LinearBoost Classifier is a rapid and accurate classification algorithm that builds upon a very fast, linear classifier.β116Updated 6 months ago
- For optimization algorithm research and development.β452Updated this week
- Highly commented implementations of Transformers in PyTorchβ129Updated last year
- Library for Jacobian descent with PyTorch. It enables optimization of neural networks with multiple losses (e.g. multi-task learning).β157Updated this week
- A tool to analyze and debug neural networks in pytorch. Use a GUI to traverse the computation graph and view the data from many differentβ¦β271Updated 3 weeks ago
- Muon optimizer for neural networks: >30% extra sample efficiency, <3% wallclock overheadβ121Updated this week
- Package for extracting and mapping the results of every single tensor operation in a PyTorch model in one line of code.β483Updated last week
- Official Implementation of "ADOPT: Modified Adam Can Converge with Any Ξ²2 with the Optimal Rate"β338Updated this week
- Official implementation of the paper "Linear Transformers with Learnable Kernel Functions are Better In-Context Models"β157Updated 9 months ago
- β129Updated last week
- Software design principles for machine learning applicationsβ298Updated last week
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"β85Updated 2 months ago
- A simple & elegant experiment tracking framework that integrates persistence logic & best practices directly into Pythonβ518Updated this week
- Actually Robust Training - Tool Inspired by Andrej Karpathy "Recipe for training neural networks". It allows you to decompose your Deepβ¦β44Updated 7 months ago
- Scalable neural net training via automatic normalization in the modular norm.β122Updated this week
- The Fastest State-of-the-Art Static Embeddings in the Worldβ478Updated this week
- Uncertainty quantification with PyTorchβ329Updated 2 weeks ago
- π JIT Implementation: Code That Writes Itselfβ100Updated last month
- β392Updated last month
- Create powerful Hydra applications without the yaml files and boilerplate code.β340Updated last week
- β240Updated last month