Comment
Section 1
throughput/tokens_per_second
throughput/tokens_per_second
log/log eval/loss
log/log eval/loss
eval/paloma/c4_en/loss
eval/paloma/c4_en/loss
log(train/loss) vs tokens
log(train/loss) vs tokens
log/log train loss
log/log train loss
Run set
6
Add a comment
Created with ❤️ on Weights & Biases.
https://wandb.ai/marin-community/marin/reports/DCLM-Debugging--Vmlldzo5NDk4MDI1