fix(mlperf-edu): anomaly-ae-train model-size gate impossible to pass (#1937)

max_model_size_kb: 32 could never be satisfied by the reference model it
gates: AnomalyDetectionAE (640/784 -> 128x4 -> 8 -> 128x4 -> 640) has
~266K parameters -- matching this same file's own `params: 0.3M` -- which
is ~1.03MB at FP32 and ~260KB even fully INT8-quantized. A submitter who
trains exactly this reference model and reports the true model size would
automatically fail the size gate regardless of reconstruction quality.

Corrected the budget to 300KB, consistent with the file's own stated 0.3M
parameter count at 1 byte/param (INT8), the standard deployment target for
this suite's "microcontroller" framing.

Author: Shashank-Tripathi-07

mlperf-edu/registry/suites/tiny/anomaly-ae-train.yaml

@@ -44,7 +44,7 @@ verified_baseline:
   epochs: 20
   time_seconds: 5
   note: Val loss intentionally higher — anomalous digits have high recon error
-max_model_size_kb: 32
+max_model_size_kb: 300
 scenario: offline
 public:
   status: score-bearing