clarify that this is bf16 mfu we're talking about

scripts/base_train.py

@@ -531,7 +531,7 @@ while True:
     else:
         eta_str = ""
     epoch = dataloader_state_dict["epoch"]
-    print0(f"step {step:05d}/{num_iterations:05d} ({pct_done:.2f}%) | loss: {debiased_smooth_loss:.6f} | lrm: {lrm:.2f} | dt: {dt * 1000:.2f}ms | tok/sec: {tok_per_sec:,} | mfu: {mfu:.2f} | epoch: {epoch} | total time: {total_training_time/60:.2f}m{eta_str}")
+    print0(f"step {step:05d}/{num_iterations:05d} ({pct_done:.2f}%) | loss: {debiased_smooth_loss:.6f} | lrm: {lrm:.2f} | dt: {dt * 1000:.2f}ms | tok/sec: {tok_per_sec:,} | bf16_mfu: {mfu:.2f} | epoch: {epoch} | total time: {total_training_time/60:.2f}m{eta_str}")
     if step % 100 == 0:
         log_data = {
             "step": step,