metadata
license: apache-2.0
LLM360 Research Suite: K2 Loss Spike 2
We encountered two major loss spikes while training K2.
- The first loss spike occured after X checkpoints and lasted over ~34 checkpoints. We restarted training at checkpoint X and training returned to normal.
- The second loss spike occured after restarting training to fix the first loss spike at checkpoint X and lasted from ~8 checkpoints.
We are releasing these checkpoints so others can study this interesting phenomena in large model training.
Purpose
Loss spikes are still a relatively unknown phenomena. By making these spikes and associated training details available, we hope others use these artifacts to further the worlds knowledge on this topic.
All Checkpoints
| Checkpoints | |
|---|---|
| Checkpoint 186 | Checkpoint 194 |
| Checkpoint 188 | Checkpoint 196 |
| Checkpoint 190 | Checkpoint 198 |
| Checkpoint 192 | Checkpoint 200 |
[to find all branches: git branch -a]
Loss Spike's on the LLM360 Evaluation Suite
something here
About the LLM360 Research Suite
The LLM360 Research Suite is a comprehensive set of large language model (LLM) artifacts from Amber, CrystalCoder, and K2 for academic and industry researchers to explore LLM training dynamics. Additional resources can be found at llm360.ai.