learning_rate,run,global_step,epoch,final_eval_step,final_eval_loss,min_eval_step,min_eval_loss,max_grad_norm,p95_grad_norm,train_runtime,eval_observations,gradient_observations
8e-05,lr_0p00008,18688,1.0,18688,0.875216543674469,18688,0.875216543674469,9.149866104125977,1.5837211608886719,79243.6449,19,1868
0.0001,lr_0p00010,18688,1.0,18688,0.87261962890625,18688,0.87261962890625,8.578277587890625,1.6475107669830322,79344.5851,19,1868
0.00015,lr_0p00015,18688,1.0,18688,0.8842697143554688,18688,0.8842697143554688,28.051427841186523,1.9590225219726562,80127.6428,19,1868
0.00018,lr_0p00018,18688,1.0,18688,0.8914602994918823,18000,0.891387939453125,6.5584211349487305,2.163313627243042,79892.0077,19,1868
0.0002,lr_0p00020,18688,1.0,18688,0.8976690173149109,18000,0.897506594657898,10.969125747680664,2.306173801422119,79710.3252,19,1868
0.00023,lr_0p00023,18688,1.0,18688,0.9032362699508667,18000,0.9031931161880493,23.10581398010254,2.501060724258423,79789.3562,19,1868