pikaliov 46b1208891 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>

2026-04-21 21:21:56 +03:00

..

balanced.gin

Rewrite: GatedFusion architecture + UAV-GeoLoc dataset

2026-04-17 17:13:00 +03:00

baseline_no_text.gin

Rewrite: GatedFusion architecture + UAV-GeoLoc dataset

2026-04-17 17:13:00 +03:00

gtauav_balanced.gin

Add gradient accumulation support

2026-04-21 21:21:56 +03:00

gtauav_baseline.gin

Add ML diagnostics tooling (W&B, TensorBoard, Grad-CAM, profiler) and gin configs

2026-04-21 20:30:50 +03:00

gtauav_image_heavy.gin

Add ML diagnostics tooling (W&B, TensorBoard, Grad-CAM, profiler) and gin configs

2026-04-21 20:30:50 +03:00

gtauav_text_heavy.gin

Add ML diagnostics tooling (W&B, TensorBoard, Grad-CAM, profiler) and gin configs

2026-04-21 20:30:50 +03:00

text_heavy.gin

Rewrite: GatedFusion architecture + UAV-GeoLoc dataset

2026-04-17 17:13:00 +03:00