Spaces:

chane35
/

permanence

Sleeping

App Files Files Community

permanence / results

540 kB

Ctrl+K

Ctrl+K

1 contributor

History: 4 commits

chane35's picture

PERMANENCE training: 4-stage SFT -> gate -> GRPO -> eval pipeline

b111201 verified 3 months ago

README.md

892 Bytes
PERMANENCE training: 4-stage SFT -> gate -> GRPO -> eval pipeline 3 months ago
comparison.csv

5.97 kB
PERMANENCE training: 4-stage SFT -> gate -> GRPO -> eval pipeline 3 months ago
confusion_matrix.png

56.3 kB
PERMANENCE training: 4-stage SFT -> gate -> GRPO -> eval pipeline 3 months ago
results.json

691 Bytes
PERMANENCE training: 4-stage SFT -> gate -> GRPO -> eval pipeline 3 months ago
reward_comparison.png

56.8 kB
PERMANENCE training: 4-stage SFT -> gate -> GRPO -> eval pipeline 3 months ago
summary.txt

1.69 kB
PERMANENCE training: 4-stage SFT -> gate -> GRPO -> eval pipeline 3 months ago
training_log.json

292 kB
PERMANENCE training: 4-stage SFT -> gate -> GRPO -> eval pipeline 3 months ago
training_reward_curve.png

125 kB
xet

PERMANENCE training: 4-stage SFT -> gate -> GRPO -> eval pipeline 3 months ago