| step,train_loss,val_loss,lr,grad_norm,dt_ms,tok_per_sec,timer_data,timer_fwd,timer_loss,timer_bwd,timer_clip,timer_optim,mem_gpu_mb | |
| 0,11.160557,-1.000000,0.000007,86.484985,1223.233276,6697.005517,3.181440,971.718262,3.670816,66.766365,9.957504,124.290466,22558.937500 | |