Buckets:
| # Queue 3: waits for P1 (pid 41291), then P2o, P2s, E5-proc (notes -> train -> eval), E2o, E2s, latency. | |
| cd /workspace/think-decide | |
| export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True | |
| while kill -0 41291 2>/dev/null; do sleep 15; done | |
| scripts/run_proc_arm.sh p2o --n-think 32 --k-choices 1,2,4,8 --budget 42000 --gate-init 0.014 > logs/p2o_run.out 2>&1 | |
| scripts/run_proc_arm.sh p2s --n-think 32 --k-choices 1,2,4,8 --budget 36000 --fb-mode soft --gate-init 1.0 --gate-fixed > logs/p2s_run.out 2>&1 | |
| scripts/run_e5_proc.sh > logs/p5_run.out 2>&1 | |
| scripts/run_arm.sh e2o --n-think 32 --k-choices 1,2,4,8 --budget 42000 --gate-init 0.014 > logs/e2o_run.out 2>&1 | |
| scripts/run_arm.sh e2s --n-think 32 --k-choices 1,2,4,8 --budget 36000 --fb-mode soft --gate-init 1.0 --gate-fixed > logs/e2s_run.out 2>&1 | |
| python src/latency.py --model runs/e2/model.safetensors > logs/latency.log 2>&1 | |
| echo QUEUE3_DONE > logs/queue3.done | |
Xet Storage Details
- Size:
- 927 Bytes
- Xet hash:
- f3d7be5a2708bde52b32fc4174ae6bada1d5df5efed14f05f118b172975db54b
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.