Skip to main content
patjj
Projects
literature_search
Log in
Sign up
Overview
Workspace
Runs
Automat.
Sweeps
Reports
Artifacts
Pj20's workspace
Personal workspace
Automated workspace
Changes are only visible to you.
Runs (12)
Name
(1 visualized)
literature_search_3b_continue
literature_search_3b_continue
literature_search_3b
literature_search_3b
first_run
first_run
literature_search_3b
literature_search_3b
literature_search_3b
literature_search_3b
literature_search_3b
literature_search_3b
literature_search_3b
literature_search_3b
literature_search_3b
literature_search_3b
literature_search_3b
literature_search_3b
literature_search_3b
literature_search_3b
literature_search_3b
literature_search_3b
literature_search_3b
literature_search_3b
1-12
of 12
Settings
Add panels
reward
9
1-9 of 9
reward/wrong_answer_ratio
reward/wrong_answer_ratio
500
1k
1.5k
2k
2.5k
Step
0
0.1
0.2
0.3
0.4
0.5
0.6
reward/mean
reward/mean
500
1k
1.5k
2k
2.5k
Step
-2
-1
0
1
2
3
4
reward/format_error_ratio
reward/format_error_ratio
500
1k
1.5k
2k
2.5k
Step
0
0.2
0.4
0.6
0.8
reward/70_recall_ratio
reward/70_recall_ratio
500
1k
1.5k
2k
2.5k
Step
0
0.1
0.2
0.3
0.4
reward/50_recall_ratio
reward/50_recall_ratio
500
1k
1.5k
2k
2.5k
Step
0.1
0.2
0.3
0.4
0.5
0.6
reward/40_recall_ratio
reward/40_recall_ratio
500
1k
1.5k
2k
2.5k
Step
0.2
0.4
0.6
reward/30_recall_ratio
reward/30_recall_ratio
500
1k
1.5k
2k
2.5k
Step
0.2
0.4
0.6
0.8
reward/10_recall_ratio
reward/10_recall_ratio
500
1k
1.5k
2k
2.5k
Step
0.2
0.4
0.6
0.8
reward/5_recall_ratio
reward/5_recall_ratio
500
1k
1.5k
2k
2.5k
Step
0.2
0.4
0.6
0.8
actor
6
1-6 of 6
critic
23
1-6 of 23
global_seqlen
6
1-6 of 6
mfu
2
prompt_length
4
1-4 of 4
response_length
4
1-4 of 4
timing_per_token_ms
6
1-6 of 6
timing_s
9
1-6 of 9
System
22
1-6 of 22
Add section