arXiv (All)
open access
Forking: Sudden Overfitting Under Replay
This paper studies forking, a generalization failure discovered in NanoGPT autoresearch. Under data replay, models with an over-encoding n-gram memory branch show a sharp separation of training and validation loss at epoch boundaries, resembling the shape of forks. We study this phenomenon in a cont
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Phase Transition Frequency as a Training Time Predictor of Test Accuracy in ResNets#972138
- AcOrch: Accelerating Sampling-based GNN Training under CPU-NPU Heterogeneous Environments#246523
- Local Evidence and Geometric Readout Repair in Trained GNNs#1063303
- Good Pretraining, Bad SFT: Checkpoint Quality Across the Training Stack#668084
- Adam-State Resets Rarely Flip Fourier Basin Selection in an N=257 Grokking Regime#691087
Record · ID 1155329
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive