Add gradient accumulation support

- New config field grad_accum_steps (default=1, no change in behavior)
- Loss scaled by 1/accum, optimizer step every N micro-batches
- Scheduler counts optimizer steps (not micro-batches)
- CLI flag --grad-accum for override
- Document gradient accumulation and in-batch negatives in README

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

conf/gtauav_balanced.gin

@@ -15,6 +15,7 @@ TrainConfigGTAUAV.learning_rate = 1e-4
 TrainConfigGTAUAV.text_lr_factor = 0.1
 TrainConfigGTAUAV.weight_decay = 1e-4
 TrainConfigGTAUAV.grad_clip = 1.0
+TrainConfigGTAUAV.grad_accum_steps = 1
 TrainConfigGTAUAV.use_amp = True
 TrainConfigGTAUAV.eval_every = 2
 TrainConfigGTAUAV.warmup_epochs = 2