REVIEW 7 cited by
Deconstructing What Makes a Good Optimizer for Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Training language models becomes increasingly expensive with scale, prompting numerous attempts to improve optimization efficiency. Despite these efforts, the Adam optimizer remains the most widely used, due to a prevailing view that it is the most effective approach. We aim to compare several optimization algorithms, including SGD, Adafactor, Adam, Lion, and Sophia in the context of autoregressive language modeling across a range of model sizes, hyperparameters, and architecture variants. Our findings indicate that, except for SGD, these algorithms all perform comparably both in their optimal performance and also in terms of how they fare across a wide range of hyperparameter choices. Our results suggest to practitioners that the choice of optimizer can be guided by practical considerations like memory constraints and ease of implementation, as no single algorithm emerged as a clear winner in terms of performance or stability to hyperparameter misspecification. Given our findings, we further dissect these approaches, examining two simplified versions of Adam: a) signed momentum (Signum) which we see recovers both the performance and hyperparameter stability of Adam and b) Adalayer, a layerwise variant of Adam which we introduce to study the impact on Adam's preconditioning for different layers of the network. Examining Adalayer leads us to the conclusion that, perhaps surprisingly, adaptivity on both the last layer and LayerNorm parameters in particular are necessary for retaining performance and stability to learning rate.
Forward citations
Cited by 7 Pith papers
-
Muon Meets Mamba: Spectral Optimization for State Space Models
On Mamba-2 130M, Muon on the output projection alone gives lower validation loss and better token efficiency than Muon on the input projection or on both, across corpora and budgets.
-
OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers
A meta-pipeline plus LMO four-axis view yields a dual taxonomy of 108 optimizers, and a multi-objective LLM/vision benchmark shows no single family dominates the quality–cost–memory frontier.
-
Prototype Transformer: Towards Language Model Architectures Interpretable by Design
ProtoT is an autoregressive language model whose attention is replaced by learned prototype channels that are claimed to capture nameable concepts and allow targeted edits, at linear sequence cost but with slightly lo...
-
Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling
When a cosine schedule would halve the learning rate, Seesaw cuts it by √2 and doubles the batch, matching loss curves with ~36% fewer serial steps.
-
Is your batch size the problem? Revisiting the Adam-SGD gap in language modeling
SGD with momentum can match Adam's performance in language modeling when trained with small batches and careful tuning, a result that contradicts several popular explanations for the optimizer gap.
-
On Design Principles for Private Adaptive Optimizers
A theoretical and empirical study finds that unbiased second-moment estimates in private Adam can be harmful in high dimensions, and that scale-then-privatize outperforms the alternatives on a small transformer task.
-
Taming LLMs by Scaling Learning Rates with Gradient Grouping
An optimizer wrapper that clusters per-layer momentum and scales learning rates by cluster-wise median deviations improves perplexity and accuracy across LLM and MLLM training, and lets LoRA pretraining approach full-...
Discussion (0). Sign in to comment.