Sorry's workspace
Runs
51
Name
0 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
alpha
awac_scale
batch_size
betas
checkpoint_dir
checkpoint_interval
chunk_size
cliprange
cliprange_value
cql_scale
epochs
eval_interval
gamma
gen_kwargs.do_sample
gen_kwargs.max_length
gen_kwargs.min_length
gen_kwargs.top_k
gen_kwargs.top_p
horizon
init_kl_coef
lam
learning_rate_init
learning_rate_target
lr_decay_steps
lr_init
lr_ramp_steps
lr_target
method.alpha
method.awac_scale
method.betas
method.chunk_size
method.cliprange
method.cliprange_reward
method.cliprange_value
method.cql_scale
method.gamma
method.gen_kwargs.do_sample
method.gen_kwargs.max_length
method.gen_kwargs.min_length
method.gen_kwargs.top_k
method.gen_kwargs.top_p
method.horizon
method.init_kl_coef
Crashed
-
sorry
2h 49m 31s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
0.001
1
[4]
-
-
-
-
0.1
0.99
-
-
-
-
-
-
-
1-1
of 1