Agatamlyn's workspace
Runs
3
State
Notes
User
Tags
Created
Runtime
Sweep
train/entropy
train/exception_rate
train/grad_norm
train/independent_reward
train/loss
train/policy_loss
train/reward
train/reward_std_dev
train/ruler_score
training_step
Finished
morgan
5s
-
-
-
-
-
-
-
-
-
-
-
Finished
morgan
33m 24s
-
-
-
-
-
-
-
-
0
-
1
Finished
morgan
4h 6m 9s
-
0.063932
0
0.35005
0
0.19687
0.19686
0.175
0.055902
0.175
6
1-3
of 3