Spaces:

garvitsachdeva
/

SpindleFlow-RL

Runtime error

App Files Files Community

SpindleFlow-RL

Commit History

Apr 26

15:10
fix: remove root app.py — HF defaults to app.py over app_file setting

garvitsachdeva

68ba0c4
14:41
fix: downgrade sdk_version 1.44.0→1.40.0 — HF health check compatibility

garvitsachdeva

fc19138
14:23
diag: minimal 5-line app + disable usage stats — isolate Starting issue

garvitsachdeva

066febe
14:15
fix: cache_resource warm-up — spinner flushes before heavy imports block

garvitsachdeva

f7e6177
12:21
diag: print checkpoints + visible loading banner; expose errors to stderr

garvitsachdeva

1c14ec3
12:17
fix: call set_page_config before heavy imports; patch duplicate call

garvitsachdeva

b5fdc1f
12:13
fix: use exec() wrapper — eliminates double set_page_config crash

garvitsachdeva

96cef35
11:54
fix: set_page_config before heavy import; cache_resource spinner; no-op patch

garvitsachdeva

a824fc0
11:32
fix: importlib wrapper with correct __file__; remove garbage files

garvitsachdeva

61e8a52
11:23
diag: wrap module-level imports to surface crash error⁠

garvitsachdeva +1: Claude Sonnet 4.6

51db558
11:21
fix: move streamlit_app.py to root; fix sys.path for new location⁠

garvitsachdeva +1: Claude Sonnet 4.6

9dfb393
11:18
fix: use app.py as Streamlit entry point (HF default)⁠

garvitsachdeva +1: Claude Sonnet 4.6

37c9261
11:16
diag: minimal test to confirm Space runs our file

garvitsachdeva

92182bf
11:10
fix: add openenv back; catch BaseException to surface crash cause⁠

garvitsachdeva +1: Claude Sonnet 4.6

72d70ca
11:07
blog added

garvitsachdeva

64a490d
11:06
fix: use importlib to load demo app + streamlit config.toml⁠

garvitsachdeva +1: Claude Sonnet 4.6

e05a5b9
11:01
fix: catch startup errors and display them instead of crash-looping⁠

garvitsachdeva +1: Claude Sonnet 4.6

e247c59
10:58
fix: use exec() to run demo app with correct __file__ context⁠

garvitsachdeva +1: Claude Sonnet 4.6

b0a7802
10:55
fix: add root streamlit_app.py entry point; HF was running default demo⁠

garvitsachdeva +1: Claude Sonnet 4.6

fba2beb
10:36
feat: add Training Space link to Training tab; fix Space URL in app.py⁠

garvitsachdeva +1: Claude Sonnet 4.6

9988949
10:30
deploy: Streamlit Space setup + button-triggered training⁠

garvitsachdeva +1: Claude Sonnet 4.6

7e20750
10:19
final commits

garvitsachdeva

b6f7301
08:40
fix: quality demo

garvitsachdeva

c699da7
07:25
trained evironment UI fixes

garvitsachdeva

44f11d2
05:50
fix: install nvidia-cudnn-cu12 alongside CUDA torch (removes --no-deps)

garvitsachdeva

0c3df82
05:44
fix: force-reinstall CUDA torch before gradio import; populate logs on page load

garvitsachdeva

82cc86d
05:33
fix: eliminate API leaks in training loop, set 30k steps for A100

garvitsachdeva

a5c7dd0
05:13
Fix CPU training + 1902ms step speed bottleneck

garvitsachdeva

e8360fd
04:59
fix: push reward curve + logs every 10k steps, not just at training end

garvitsachdeva

a798c01
04:55
perf: add encode+step benchmark to logs, validate CUDA speed

garvitsachdeva

812dbcc
04:49
perf: force ST to CUDA, disable LLM tasks, reduce to 100k steps

garvitsachdeva

b71b25c
04:36
feat: integrate trained RecurrentPPO policy into Streamlit demo UI

garvitsachdeva

236d9fb
04:19
fix: force-install CUDA torch in app.py before training starts

garvitsachdeva

83cf44b
04:07
fix: remove torch from requirements to preserve pre-installed CUDA torch

garvitsachdeva

c977821
03:52
fix: install CUDA-enabled torch for GPU spaces

garvitsachdeva

a39792d
03:35
pre-deployment fixes for HF Spaces

garvitsachdeva

aa154f2

Apr 25

19:31
Update Cell 1 & 2 with user-verified working versions⁠

garvitsachdeva +1: Claude Sonnet 4.6

175b600
19:23
Bulletproof Cell 1: check .git dir, rm partial clone, correct REPO path⁠

garvitsachdeva +1: Claude Sonnet 4.6

3bce6e3
19:18
Fix REPO path: clone root is /content/kuchbhi not /content/kuchbhi/spindleflow-rl⁠

garvitsachdeva +1: Claude Sonnet 4.6

21923ce
19:14
Rewrite train_colab.py: clean cells, fix audioop-lts, log file, reward curve⁠

garvitsachdeva +1: Claude Sonnet 4.6

956acce
19:12
Remove Colab notebook — using plain .py script instead⁠

garvitsachdeva +1: Claude Sonnet 4.6

c8407b4
19:08
Fix Cell 1: skip audioop-lts on Python < 3.13 (Colab uses 3.12)⁠

garvitsachdeva +1: Claude Sonnet 4.6

c77f83c
19:00
Add Colab notebook: 8 runnable cells, both secrets, log + curve⁠

garvitsachdeva +1: Claude Sonnet 4.6

13dd91f
18:54
Final Colab training script: log file, fixed reward curve, 100k steps⁠

garvitsachdeva +1: Claude Sonnet 4.6

c2b373f
18:49
Add HF Hub push cell + fix pip deps in Colab training script⁠

garvitsachdeva +1: Claude Sonnet 4.6

8e0fa29
18:40
Remove gr.Timer: caused C-level crash with no Python output⁠

garvitsachdeva +1: Claude Sonnet 4.6

278b691
18:34
Fix logs not showing: use file-based state instead of in-memory globals⁠

garvitsachdeva +1: Claude Sonnet 4.6

52e0424
18:05
Add auto-refresh timer and dark theme CSS⁠

garvitsachdeva +1: Claude Sonnet 4.6

0c2a6e7
17:53
Fix theme/css: keep in Blocks(), not launch()⁠

garvitsachdeva +1: Claude Sonnet 4.6

c0c63ff
17:46
Improve Gradio UI: fix theme, add CSS, clean up layout⁠

garvitsachdeva +1: Claude Sonnet 4.6

c0997b4

Commit History

Apr 26

fix: remove root app.py — HF defaults to app.py over app_file setting

fix: downgrade sdk_version 1.44.0→1.40.0 — HF health check compatibility

diag: minimal 5-line app + disable usage stats — isolate Starting issue

fix: cache_resource warm-up — spinner flushes before heavy imports block

diag: print checkpoints + visible loading banner; expose errors to stderr

fix: call set_page_config before heavy imports; patch duplicate call

fix: use exec() wrapper — eliminates double set_page_config crash

fix: set_page_config before heavy import; cache_resource spinner; no-op patch

fix: importlib wrapper with correct __file__; remove garbage files

diag: wrap module-level imports to surface crash error⁠

fix: move streamlit_app.py to root; fix sys.path for new location⁠

fix: use app.py as Streamlit entry point (HF default)⁠

diag: minimal test to confirm Space runs our file

fix: add openenv back; catch BaseException to surface crash cause⁠

blog added

fix: use importlib to load demo app + streamlit config.toml⁠

fix: catch startup errors and display them instead of crash-looping⁠

fix: use exec() to run demo app with correct __file__ context⁠

fix: add root streamlit_app.py entry point; HF was running default demo⁠

feat: add Training Space link to Training tab; fix Space URL in app.py⁠

deploy: Streamlit Space setup + button-triggered training⁠

final commits

fix: quality demo

trained evironment UI fixes

fix: install nvidia-cudnn-cu12 alongside CUDA torch (removes --no-deps)

fix: force-reinstall CUDA torch before gradio import; populate logs on page load

fix: eliminate API leaks in training loop, set 30k steps for A100

Fix CPU training + 1902ms step speed bottleneck

fix: push reward curve + logs every 10k steps, not just at training end

perf: add encode+step benchmark to logs, validate CUDA speed

perf: force ST to CUDA, disable LLM tasks, reduce to 100k steps

feat: integrate trained RecurrentPPO policy into Streamlit demo UI

fix: force-install CUDA torch in app.py before training starts

fix: remove torch from requirements to preserve pre-installed CUDA torch

fix: install CUDA-enabled torch for GPU spaces

pre-deployment fixes for HF Spaces

Apr 25

Update Cell 1 & 2 with user-verified working versions⁠

Bulletproof Cell 1: check .git dir, rm partial clone, correct REPO path⁠

Fix REPO path: clone root is /content/kuchbhi not /content/kuchbhi/spindleflow-rl⁠

Rewrite train_colab.py: clean cells, fix audioop-lts, log file, reward curve⁠

Remove Colab notebook — using plain .py script instead⁠

Fix Cell 1: skip audioop-lts on Python < 3.13 (Colab uses 3.12)⁠

Add Colab notebook: 8 runnable cells, both secrets, log + curve⁠

Final Colab training script: log file, fixed reward curve, 100k steps⁠

Add HF Hub push cell + fix pip deps in Colab training script⁠

Remove gr.Timer: caused C-level crash with no Python output⁠

Fix logs not showing: use file-based state instead of in-memory globals⁠

Add auto-refresh timer and dark theme CSS⁠

Fix theme/css: keep in Blocks(), not launch()⁠

Improve Gradio UI: fix theme, add CSS, clean up layout⁠

fix: importlib wrapper with correct file; remove garbage files

fix: use exec() to run demo app with correct file context⁠