| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Llama-2 7B pre-training | AdaGC | Number of Spikes0 | 9 | 4d ago | |
| Llama-2 1.3B (train) | SPAM | Number of Spikes0 | 4 | 4d ago | |
| ERNIE 10B-A1.4B (train) | AdaGC | Number of Spikes0 | 2 | 4d ago | |
| Mixtral 8x1B pre-training | AdaGC | Num Spikes0 | 2 | 4d ago |