Skip to main content
jiayipan
Projects
tinyrl
Log in
Sign up
Project
Workspace
Runs
Automat.
Sweeps
Reports
Artifacts
Jiayipan's workspace
Personal workspace
Automated workspace
Changes are only visible to you.
Runs
89
Name
3 visualized
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323181119
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323181119
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323181116
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323181116
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323180818
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323180818
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323172909
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323172909
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323172902
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323172902
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323172858
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323172858
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323172852
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323172852
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323061631
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323061631
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323061555
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323061555
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323061432
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323061432
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323061356
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323061356
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323061304
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323061304
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323055926
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323055926
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323055207
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323055207
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323054530
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323054530
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323054421
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323054421
2048-3
2048-3
4096-3
4096-3
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250321151640
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250321151640
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250321151351
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250321151351
1-20
of 89
avg_reward
avg_reward
0
20
40
60
80
100
Step
0.45
0.5
0.55
0.6
0.65
0.7
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323181119
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323181116
grpo_llama-hsp-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250323180818
Previous
Next