Spaces:

israaaML
/

fsds_cleaning_env

Running

App Files Files Community

fsds_cleaning_env

303 kB

2 contributors

History: 6 commits

israaaML's picture

Claude Sonnet 4.6

add compare_agents.py: 4-way benchmark (Random/Heuristic/SFT/GRPO)

2968ead 1 day ago

configs
v2: curriculum scheduling, SFT pipeline, reward redesign, agent guide 1 day ago
examples
v3: benchmark results, final report, agent/eval improvements, smoke test fixes 1 day ago
server
fix: sanitize numpy/pandas types in submit_solution JSON serialization 1 day ago
tests
v2: curriculum scheduling, SFT pipeline, reward redesign, agent guide 1 day ago
training
v2: curriculum scheduling, SFT pipeline, reward redesign, agent guide 1 day ago
.dockerignore

80 Bytes

v2: curriculum scheduling, SFT pipeline, reward redesign, agent guide 1 day ago
.gitattributes

1.52 kB

initial commit 2 days ago
.gitignore

109 Bytes

v2: curriculum scheduling, SFT pipeline, reward redesign, agent guide 1 day ago
AGENT_GUIDE.md

17.5 kB

v2: curriculum scheduling, SFT pipeline, reward redesign, agent guide 1 day ago
AGENT_PLAN.md

11 kB

v2: curriculum scheduling, SFT pipeline, reward redesign, agent guide 1 day ago
Dockerfile

574 Bytes

Upload folder using huggingface_hub 2 days ago
FINAL_REPORT.md

8.09 kB

v3: benchmark results, final report, agent/eval improvements, smoke test fixes 1 day ago
README.md

9.69 kB

v2: curriculum scheduling, SFT pipeline, reward redesign, agent guide 1 day ago
__init__.py

520 Bytes

v2: curriculum scheduling, SFT pipeline, reward redesign, agent guide 1 day ago
agents.py

16.9 kB

v3: benchmark results, final report, agent/eval improvements, smoke test fixes 1 day ago
benchmark_guides.md

4.42 kB

v3: benchmark results, final report, agent/eval improvements, smoke test fixes 1 day ago
client.py

502 Bytes

Upload folder using huggingface_hub 2 days ago
compare_agents.py

7.33 kB

add compare_agents.py: 4-way benchmark (Random/Heuristic/SFT/GRPO) 1 day ago
curriculum.py

8.6 kB

v2: curriculum scheduling, SFT pipeline, reward redesign, agent guide 1 day ago
dataset_generators.py

16.7 kB

v3: benchmark results, final report, agent/eval improvements, smoke test fixes 1 day ago
demonstrations.py

18.5 kB

v2: curriculum scheduling, SFT pipeline, reward redesign, agent guide 1 day ago
evaluate_agent.py

6.03 kB

v3: benchmark results, final report, agent/eval improvements, smoke test fixes 1 day ago
evaluation_tasks.py

2.21 kB

v2: curriculum scheduling, SFT pipeline, reward redesign, agent guide 1 day ago
metrics.py

4.65 kB

v2: curriculum scheduling, SFT pipeline, reward redesign, agent guide 1 day ago
model.py

106 Bytes

Upload folder using huggingface_hub 2 days ago
models.py

1.17 kB

Upload folder using huggingface_hub 2 days ago
openenv.yaml

100 Bytes

Upload folder using huggingface_hub 2 days ago
plan_results.md

22.5 kB

v2: curriculum scheduling, SFT pipeline, reward redesign, agent guide 1 day ago
project_recommendations.md

7.36 kB

v2: curriculum scheduling, SFT pipeline, reward redesign, agent guide 1 day ago
pyproject.toml

909 Bytes

v2: curriculum scheduling, SFT pipeline, reward redesign, agent guide 1 day ago
results_heuristic.json

14.4 kB

v3: benchmark results, final report, agent/eval improvements, smoke test fixes 1 day ago
results_llm.json

12.1 kB

v3: benchmark results, final report, agent/eval improvements, smoke test fixes 1 day ago
results_random.json

13.9 kB

v3: benchmark results, final report, agent/eval improvements, smoke test fixes 1 day ago
reward.py

2.17 kB

v2: curriculum scheduling, SFT pipeline, reward redesign, agent guide 1 day ago
training_colab.py

16 kB

v3: benchmark results, final report, agent/eval improvements, smoke test fixes 1 day ago
training_sft.py

7.37 kB

v2: curriculum scheduling, SFT pipeline, reward redesign, agent guide 1 day ago