Moeblack/longzu-dpo-lora
0
Training in progress, step 44
full ckpt checkpoint-44
cleanup tokentest
tokentest
full ckpt checkpoint-60 (含 optimizer.pt/scheduler.pt)
Training in progress, step 60
full ckpt checkpoint-1 (含 optimizer.pt/scheduler.pt)
Training in progress, step 1
full ckpt checkpoint-1 (含 optimizer.pt/scheduler.pt)
Training in progress, step 1
dpo v1 final
Training in progress, step 1
initial commit
