GPT-J: perplexity for checkpoints

[Daniel Khashabi]

Thanks for sharing the checkpoints!
Wondering if there is a plot of perplexity as a function of steps #?

[Ben Wang]

Information collected during training (ppl, evals etc) can be seen here: https://wandb.ai/eleutherai/mesh-transformer-jax/reports/6B-Rotary--Vmlldzo2NDQxNzY