🌀️ Conversations with AI — 338

Next,

@help @damages tensorboard

@damages tensorboard - <model-report-id>

model:

Maui-Hawaii-fires-Aug-23-model-2025-01-10-NQb8IS

@damages tensorboard - \
    Maui-Hawaii-fires-Aug-23-model-2025-01-10-NQb8IS

https://github.com/kamangir/awesome-bash-cli/pull/49: pipeline ✅ review ✅ merge ✅ upgrade ✅

@git abcli checkout current rebuild
@init

install.sh: line 4: blue_sandbox_microsoft_building_damage_assessment_install: command not found

@damages install recreate_env

https://github.com/kamangir/blue-sandbox/pull/6: pipeline ✅ review ✅ merge ✅ upgrade ✅

@git blue-sandbox checkout main rebuild
@sandbox init
@git blue-sandbox create_branch microsoft-building-damage-assessment

@seed list

@seed sagemaker-system screen

using, github/kamangir/notebooks-and-scripts/SageMaker.md

@seed sagemaker screen

@git clone blue-sandbox install

@damages install

On Sagemaker.

Sanity Checking: | | 0/? [00:00<?, ?it/s]/opt/conda/envs/bda/lib/python3.10/site-packages/torch/utils/data/dataloader.py:617: UserWarning: This DataLoader will create 24 worker processes in total. Our suggested max number of worker in current system is 4, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary. ⚠️

ERROR: Unexpected bus error encountered in worker. This might be caused by insufficient shared memory (shm). ⚠️

ml.g4dn.8xlarge

ml.g4dn.12xlarge

num_workers=6 started in p-ml-g4dn-xlarge,

min_epochs=10, 🤔

seems a lot slower than I expected. 🤔

Maui-Hawaii-fires-Aug-23-model-2025–01–11-RHZZnn ⏬

https://github.com/kamangir/awesome-bash-cli/pull/50: pipeline ✅ review ✅ merge ✅ upgrade ✅

@git abcli checkout current rebuild
@init

ml-g4dn-2xlarge

@seed sagemaker
@damages install

Maui-Hawaii-fires-Aug-23-model-2025–01–11-tEGj0W ⏬

continues.