Skip to main content
ucalyptus
Projects
Search-R1
Log in
Sign up
Overview
Workspace
Runs
Automat.
Sweeps
Reports
Artifacts
Ucalyptus's workspace
Personal workspace
Automated workspace
Changes are only visible to you.
Runs (1)
Name
(1 visualized)
nq-search-r1-ppo-llama3.2-3b-em
nq-search-r1-ppo-llama3.2-3b-em
1-1
of 1
Settings
Add panels
actor
6
1-6 of 6
actor/ppo_kl
actor/ppo_kl
50
100
150
200
250
Step
-0.01
-0.005
0
0.005
0.01
nq-search-r1-ppo-llama3.2-3b-em
actor/pg_loss
actor/pg_loss
50
100
150
200
250
Step
-0.3
-0.2
-0.1
0
0.1
0.2
0.3
nq-search-r1-ppo-llama3.2-3b-em
actor/pg_clipfrac
actor/pg_clipfrac
50
100
150
200
250
Step
0
0.002
0.004
0.006
0.008
nq-search-r1-ppo-llama3.2-3b-em
actor/lr
actor/lr
50
100
150
200
250
Step
2e-7
4e-7
6e-7
8e-7
0.000001
nq-search-r1-ppo-llama3.2-3b-em
actor/grad_norm
actor/grad_norm
50
100
150
200
250
Step
2
4
6
8
10
nq-search-r1-ppo-llama3.2-3b-em
actor/entropy_loss
actor/entropy_loss
50
100
150
200
250
Step
0.5
1
1.5
2
nq-search-r1-ppo-llama3.2-3b-em
critic
23
1-6 of 23
global_seqlen
6
1-6 of 6
Add section