Mingyuc's workspace
Runs
19
Name
19 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
actor_rollout_ref.actor.adv_estimator
actor_rollout_ref.actor.beta
actor_rollout_ref.actor.clip_ratio
actor_rollout_ref.actor.conservative
actor_rollout_ref.actor.entropy_coeff
actor_rollout_ref.actor.fsdp_config.fsdp_size
actor_rollout_ref.actor.fsdp_config.grad_offload
actor_rollout_ref.actor.fsdp_config.optimizer_offload
actor_rollout_ref.actor.fsdp_config.param_offload
actor_rollout_ref.actor.fsdp_config.wrap_policy.min_num_params
actor_rollout_ref.actor.grad_clip
actor_rollout_ref.actor.kl_loss_coef
actor_rollout_ref.actor.kl_loss_type
actor_rollout_ref.actor.loss_type
actor_rollout_ref.actor.normalize_g
actor_rollout_ref.actor.normalize_logprob
actor_rollout_ref.actor.optim.lr
actor_rollout_ref.actor.optim.lr_warmup_steps_ratio
actor_rollout_ref.actor.optim.total_training_steps
actor_rollout_ref.actor.optim.warmup_style
actor_rollout_ref.actor.ppo_epochs
actor_rollout_ref.actor.ppo_max_token_len_per_gpu
actor_rollout_ref.actor.ppo_micro_batch_size
actor_rollout_ref.actor.ppo_mini_batch_size
actor_rollout_ref.actor.shuffle
actor_rollout_ref.actor.strategy
actor_rollout_ref.actor.ulysses_sequence_parallel_size
actor_rollout_ref.actor.use_dynamic_bsz
actor_rollout_ref.actor.use_kl_loss
actor_rollout_ref.hybrid_engine
actor_rollout_ref.model.enable_gradient_checkpointing
actor_rollout_ref.model.path
actor_rollout_ref.model.use_remove_padding
actor_rollout_ref.ref.fsdp_config.fsdp_size
actor_rollout_ref.ref.fsdp_config.param_offload
actor_rollout_ref.ref.fsdp_config.wrap_policy.min_num_params
actor_rollout_ref.ref.log_prob_max_token_len_per_gpu
actor_rollout_ref.ref.log_prob_micro_batch_size
actor_rollout_ref.ref.log_prob_use_dynamic_bsz
actor_rollout_ref.ref.ulysses_sequence_parallel_size
actor_rollout_ref.rollout.do_sample
actor_rollout_ref.rollout.dtype
actor_rollout_ref.rollout.enforce_eager
actor_rollout_ref.rollout.free_cache_engine
Finished
Copy of cornell-npg/qwen-final/3h6nbu99
owen-oertell
8s
-
grpo
-
0.2
-
0
-1
false
false
false
0
1
0.001
low_var_kl
-
-
-
1.0000e-7
0
1650
constant
1
16384
4
8
false
fsdp
1
false
false
true
false
Qwen/Qwen2.5-Math-7B
false
-1
false
0
16384
4
false
1
true
bfloat16
true
true
Finished
Copy of cornell-npg/qwen-final/6l02f4qm
owen-oertell
10s
-
grpo
-
0.2
-
0
-1
false
false
false
0
1
0.001
low_var_kl
-
-
-
1.0000e-7
0
1650
constant
1
16384
4
8
false
fsdp
1
false
false
true
false
Qwen/Qwen2.5-Math-7B
false
-1
false
0
16384
4
false
1
true
bfloat16
true
true
Finished
Copy of cornell-npg/qwen-final/hv77noa8
owen-oertell
6s
-
grpo
-
0.2
-
0
-1
false
false
false
0
1
0.001
low_var_kl
-
-
-
1.0000e-7
0
1650
constant
1
16384
4
8
false
fsdp
1
false
false
true
false
Qwen/Qwen2.5-Math-7B
false
-1
false
0
16384
4
false
1
true
bfloat16
true
true
Finished
Copy of cornell-npg/qwen-final/84u3gyd5
owen-oertell
5s
-
grpo
-
0.2
-
0
-1
false
false
false
0
1
0.001
low_var_kl
-
-
-
1.0000e-7
0
1650
constant
1
16384
4
8
false
fsdp
1
false
false
true
false
Qwen/Qwen2.5-Math-7B
false
-1
false
0
16384
4
false
1
true
bfloat16
true
true
Crashed
-
zg292
2d 23h 48m 21s
-
rloo
-
0.2
-
0
-1
false
false
false
0
1
0
low_var_kl
-
-
-
1.0000e-7
0
2750
constant
1
1280
4
64
false
fsdp
1
true
true
true
false
Qwen/Qwen2.5-Math-7B
false
-1
false
0
1280
4
true
1
true
bfloat16
true
true
Crashed
-
zg292
2d 23h 48m 36s
-
rloo
-
0.2
-
0
-1
false
false
false
0
1
0
low_var_kl
-
-
-
1.0000e-7
0
2750
constant
1
1280
4
64
false
fsdp
1
true
true
true
false
Qwen/Qwen2.5-Math-7B
false
-1
false
0
1280
4
true
1
true
bfloat16
true
true
Crashed
-
zg292
2d 23h 48m 51s
-
rloo
-
0.2
-
0
-1
false
false
false
0
1
0
low_var_kl
-
-
-
1.0000e-7
0
2750
constant
1
1280
4
64
false
fsdp
1
true
true
true
false
Qwen/Qwen2.5-Math-7B
false
-1
false
0
1280
4
true
1
true
bfloat16
true
true
Finished
-
wenhao-zhan
1d 7m 48s
-
gae
-
0.2
-
0
-1
false
false
false
0
1
0.001
low_var_kl
-
-
-
1.0000e-7
0
1650
constant
1
16384
4
8
false
fsdp
1
false
false
true
false
Qwen/Qwen2.5-Math-7B
false
-1
false
0
16384
4
false
1
true
bfloat16
true
true
Finished
-
wenhao-zhan
1d 10m 30s
-
gae
-
0.2
-
0
-1
false
false
false
0
1
0.001
low_var_kl
-
-
-
1.0000e-7
0
1650
constant
1
16384
4
8
false
fsdp
1
false
false
true
false
Qwen/Qwen2.5-Math-7B
false
-1
false
0
16384
4
false
1
true
bfloat16
true
true
Finished
-
wenhao-zhan
1d 13m 42s
-
gae
-
0.2
-
0
-1
false
false
false
0
1
0.001
low_var_kl
-
-
-
1.0000e-7
0
1650
constant
1
16384
4
8
false
fsdp
1
false
false
true
false
Qwen/Qwen2.5-Math-7B
false
-1
false
0
16384
4
false
1
true
bfloat16
true
true
Finished
-
wenhao-zhan
3m 24s
-
-
1
0.2
true
0
-1
false
false
false
0
1
0.001
low_var_kl
without_g
false
false
1.0000e-7
0
1650
constant
1
16384
8
8
false
fsdp
1
false
false
true
true
Qwen/Qwen2.5-Math-7B
false
-1
false
0
16384
8
false
1
true
bfloat16
true
true
Finished
-
wenhao-zhan
3m 22s
-
-
1
0.2
true
0
-1
false
false
false
0
1
0.001
low_var_kl
without_g
false
false
1.0000e-7
0
1650
constant
1
16384
8
8
false
fsdp
1
false
false
true
true
Qwen/Qwen2.5-Math-7B
false
-1
false
0
16384
8
false
1
true
bfloat16
true
true
Finished
-
wenhao-zhan
3m 33s
-
-
1
0.2
true
0
-1
false
false
false
0
1
0.001
low_var_kl
without_g
false
false
1.0000e-7
0
1650
constant
1
16384
8
8
false
fsdp
1
false
false
true
true
Qwen/Qwen2.5-Math-7B
false
-1
false
0
16384
8
false
1
true
bfloat16
true
true
Finished
-
wenhao-zhan
6h 58m 13s
-
-
1
0.2
true
0
-1
false
false
false
0
1
0.001
low_var_kl
without_g
false
false
1.0000e-7
0
1650
constant
1
16384
8
8
false
fsdp
1
false
false
true
true
Qwen/Qwen2.5-Math-7B
false
-1
false
0
16384
8
false
1
true
bfloat16
true
true
Finished
-
wenhao-zhan
6h 59m 12s
-
-
1
0.2
true
0
-1
false
false
false
0
1
0.001
low_var_kl
without_g
false
false
1.0000e-7
0
1650
constant
1
16384
8
8
false
fsdp
1
false
false
true
true
Qwen/Qwen2.5-Math-7B
false
-1
false
0
16384
8
false
1
true
bfloat16
true
true
Finished
-
wenhao-zhan
7h 40s
-
-
1
0.2
true
0
-1
false
false
false
0
1
0.001
low_var_kl
without_g
false
false
1.0000e-7
0
1650
constant
1
16384
8
8
false
fsdp
1
false
false
true
true
Qwen/Qwen2.5-Math-7B
false
-1
false
0
16384
8
false
1
true
bfloat16
true
true
Crashed
-
zg292
2d 23h 53m 5s
-
rloo
-
0.2
-
0
-1
false
false
false
0
1
0
low_var_kl
-
-
-
1.0000e-7
0
2750
constant
1
1280
4
64
false
fsdp
1
true
true
true
false
Qwen/Qwen2.5-Math-7B
false
-1
false
0
1280
4
true
1
true
bfloat16
true
true
Crashed
-
zg292
2d 23h 53m
-
rloo
-
0.2
-
0
-1
false
false
false
0
1
0
low_var_kl
-
-
-
1.0000e-7
0
2750
constant
1
1280
4
64
false
fsdp
1
true
true
true
false
Qwen/Qwen2.5-Math-7B
false
-1
false
0
1280
4
true
1
true
bfloat16
true
true
Crashed
-
zg292
2d 23h 57m 20s
-
rloo
-
0.2
-
0
-1
false
false
false
0
1
0
low_var_kl
-
-
-
1.0000e-7
0
2750
constant
1
1280
4
64
false
fsdp
1
true
true
true
false
Qwen/Qwen2.5-Math-7B
false
-1
false
0
1280
4
true
1
true
bfloat16
true
true
1-19
of 19