Spaces:

ggtejas
/

log-anomaly-env

Sleeping

App Files Files Community

log-anomaly-env

2.59 MB

Ctrl+K

Ctrl+K

1 contributor

History: 54 commits

garg-tejas

chore: add gitattributes for LFS tracking of images

4426944 7 months ago

data
feat: add TRL/GRPO training support with curriculum learning 8 months ago
docs
docs: improve README with architecture diagrams and motivation section 7 months ago
server
docs: improve README with architecture diagrams and motivation section 7 months ago
tests
docs: improve README with architecture diagrams and motivation section 7 months ago
.env.example

102 Bytes
docs: update baseline scores to Qwen3.5-9B results 8 months ago
.gitattributes

1.56 kB
chore: add gitattributes for LFS tracking of images 7 months ago
.gitignore

213 Bytes
feat: add TRL/GRPO training support with curriculum learning 8 months ago
Dockerfile

1.39 kB
feat: add winner-inspired improvements to prevent stuck agents 8 months ago
README.md

17.1 kB
docs: improve README with architecture diagrams and motivation section 7 months ago
__init__.py

1.27 kB
docs: improve README with architecture diagrams and motivation section 7 months ago
client.py

14.2 kB
feat: add TRL/GRPO training support with curriculum learning 8 months ago
config.py

9.13 kB
Align reward semantics and inference contract with latest hackathon clarifications 7 months ago
debug_model_responses.py

14.8 kB
fix: escape JSON braces in f-string and use env vars for model in debug script 8 months ago
grader.py

17.4 kB
fix: clamp rewards to 0.0-1.0 range 8 months ago
inference.py

20.1 kB
Align reward semantics and inference contract with latest hackathon clarifications 7 months ago
log_utils.py

35.8 kB
feat: winner-inspired improvements - expand reward range, add LogHub data, and hidden state/decoys 8 months ago
loghub_parser.py

26.5 kB
refactor: eliminate technical debt across codebase 8 months ago
models.py

12.1 kB
feat: winner-inspired improvements - expand reward range, add LogHub data, and hidden state/decoys 8 months ago
openenv.yaml

6.12 kB
docs: improve README with architecture diagrams and motivation section 7 months ago
pyproject.toml

2.87 kB
docs: improve README with architecture diagrams and motivation section 7 months ago
requirements.txt

310 Bytes
Add vLLM setup for baseline inference 8 months ago
run_tests.py

5.87 kB
add real log parser, remove ground truth leak 8 months ago
train_grpo.py

10.4 kB
feat: add TRL/GRPO training support with curriculum learning 8 months ago
training_client.py

16 kB
feat: add TRL/GRPO training support with curriculum learning 8 months ago
training_prompts.py

10.7 kB
feat: add TRL/GRPO training support with curriculum learning 8 months ago
uv.lock

1.38 MB
docs: improve README with architecture diagrams and motivation section 7 months ago