Spaces:

Sayuj63
/

Vapt-env

Sleeping

App Files Files Community

Vapt-env / plots

1.27 MB

Ctrl+K

Ctrl+K

1 contributor

History: 3 commits

Sayuj63's picture

Add journey/comparison/demo charts + push real model card to HF Hub

79d4df1 2 months ago

results_v1
Real GRPO results: Llama 3.2 3B avg 0.075 -> 0.482 (6.4x) on VAPT-Env 2 months ago
results_v3
Real GRPO results: Llama 3.2 3B avg 0.075 -> 0.482 (6.4x) on VAPT-Env 2 months ago
baseline_scores.json

72 Bytes
Real GRPO results: Llama 3.2 3B avg 0.075 -> 0.482 (6.4x) on VAPT-Env 2 months ago
demo_multiagent.png

78.7 kB
xet

Add journey/comparison/demo charts + push real model card to HF Hub 2 months ago
journey_progression.png

80.6 kB
xet

Add journey/comparison/demo charts + push real model card to HF Hub 2 months ago
models_comparison.png

65.5 kB
xet

Add journey/comparison/demo charts + push real model card to HF Hub 2 months ago
performance_comparison.png

54 kB
xet

Real GRPO results: Llama 3.2 3B avg 0.075 -> 0.482 (6.4x) on VAPT-Env 2 months ago
reward_per_episode.png

191 kB
xet

Real GRPO results: Llama 3.2 3B avg 0.075 -> 0.482 (6.4x) on VAPT-Env 2 months ago
trained_scores.json

89 Bytes
Real GRPO results: Llama 3.2 3B avg 0.075 -> 0.482 (6.4x) on VAPT-Env 2 months ago
training_loss.png

191 kB
xet

Real GRPO results: Llama 3.2 3B avg 0.075 -> 0.482 (6.4x) on VAPT-Env 2 months ago
wandb_run_url.txt

62 Bytes
Real GRPO results: Llama 3.2 3B avg 0.075 -> 0.482 (6.4x) on VAPT-Env 2 months ago