Spaces:

Imsachin010
/

salespath-env

Runtime error

App Files Files Community

salespath-env / training

264 kB

Ctrl+K

Ctrl+K

1 contributor

History: 20 commits

Imsachin010's picture

Fix: GRPO not in trl 0.11, need trl>=0.14.0

c4b0562 3 months ago

__pycache__
Fix: GRPO not in trl 0.11, need trl>=0.14.0 3 months ago
__init__.py

0 Bytes
first commit 3 months ago
colab_train.ipynb

29.2 kB
Automate 7B Training using Hugging Face Space Dockerfile 3 months ago
curriculum.py

1.41 kB
first commit 3 months ago
debug_episode.py

1.46 kB
first commit 3 months ago
eval_baseline_vs_trained.py

9.04 kB
HF Spaces GPU training pipeline 3 months ago
grpo_train.py

16 kB
Fix trl/pytorch version incompatibility + indentation bugs 3 months ago
hf_keepalive_app.py

5.12 kB
HF Spaces GPU training pipeline 3 months ago
plot_rewards.py

3.17 kB
fix: colab working dir bug, rollout sys.path, openenv imports, add plot_rewards 3 months ago
preflight_check.py

2.11 kB
Fix: GRPO not in trl 0.11, need trl>=0.14.0 3 months ago
rollout.py

5.34 kB
fix: colab working dir bug, rollout sys.path, openenv imports, add plot_rewards 3 months ago
test_rollout.py

1.87 kB
fix: add training dir to sys.path so -m training.test_rollout works on Colab 3 months ago
train7b.ipynb

3.64 kB
Automate 7B Training using Hugging Face Space Dockerfile 3 months ago
traingrpo.ipynb

150 kB
Update blog with 0.5B results and project metrics 3 months ago