Fix one-epoch track GRU smoke launcher
This commit is contained in:
@@ -60,6 +60,11 @@ The existing EasyCom local sidecars already contain crop features, frame times,
|
||||
source-clip indices and person IDs; this experiment does not require feature
|
||||
re-extraction.
|
||||
|
||||
Runtime status (2026-09-07): the focused causal-history, exact-zero-gate and
|
||||
train/infer round-trip tests passed in 49.699 seconds on the remote PyTorch/L20
|
||||
environment. This verifies the code path, not model quality. The one-session
|
||||
GPU training smoke and full experiment remain unmeasured.
|
||||
|
||||
## Fair initialization
|
||||
|
||||
`track-gru-residual` requires `--initialize-pooled-checkpoint`. The loader
|
||||
@@ -103,6 +108,9 @@ CUDA_VISIBLE_DEVICES=0 \
|
||||
bash run_easycom_track_gru_residual.sh all 0
|
||||
```
|
||||
|
||||
For `EPOCHS=1`, the launcher automatically uses zero warmup unless
|
||||
`WARMUP_EPOCHS` is explicitly supplied.
|
||||
|
||||
Then use three GPUs in three foreground terminals. These runs report Session
|
||||
12 development scores, not the official test set:
|
||||
|
||||
|
||||
Reference in New Issue
Block a user