Buckets:
| set -euo pipefail | |
| pip install --no-cache-dir datasets==4.8.4 | |
| python /work/code/repro_experiment.py \ | |
| --device cuda \ | |
| --train-size 8192 \ | |
| --eval-size 1024 \ | |
| --vocab-size 12000 \ | |
| --seq-len 64 \ | |
| --width 192 \ | |
| --depth 8 \ | |
| --rank 1 \ | |
| --batch-size 128 \ | |
| --steps 400 \ | |
| --eval-every 25 \ | |
| --threshold 0.55 \ | |
| --perturbations 1 \ | |
| --lr-bp 0.003 \ | |
| --lr-fmad 0.001 \ | |
| --lr-zo 0.001 \ | |
| --seed 0 \ | |
| --output-dir /work/seed0 | |
Xet Storage Details
- Size:
- 462 Bytes
- Xet hash:
- db70f78eb20db4697255a5cb0e667d6b341f898381984f81f664bdbcc90c2783
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.