Yipingwang22's workspace
Runs
21
Name
2 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
actor_rollout_ref.actor.clip_ratio
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.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_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.model.use_think
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_use_dynamic_bsz
actor_rollout_ref.ref.ulysses_sequence_parallel_size
actor_rollout_ref.rollout.disable_log_stats
actor_rollout_ref.rollout.do_sample
actor_rollout_ref.rollout.dtype
actor_rollout_ref.rollout.enable_chunked_prefill
actor_rollout_ref.rollout.enforce_eager
actor_rollout_ref.rollout.free_cache_engine
actor_rollout_ref.rollout.gpu_memory_utilization
actor_rollout_ref.rollout.ignore_eos
actor_rollout_ref.rollout.load_format
actor_rollout_ref.rollout.log_prob_max_token_len_per_gpu
actor_rollout_ref.rollout.log_prob_use_dynamic_bsz
actor_rollout_ref.rollout.max_num_batched_tokens
Crashed
adaptiveSeek
yipingwang22
4d 10h 24m 7s
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
4000
constant
1
32768
128
false
fsdp
1
true
true
true
true
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
true
-
true
0
32768
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
32768
true
8192
Finished
adaptiveSeek
yipingwang22
4d 7h 44m 56s
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
4000
constant
1
32768
128
false
fsdp
1
true
true
true
true
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
true
true
true
0
32768
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
32768
true
8192
Crashed
adaptiveSeek
yipingwang22
6d 12h 21m 46s
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
4000
constant
1
32768
128
false
fsdp
1
true
true
true
true
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
true
true
true
0
32768
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
32768
true
8192
Crashed
adaptiveSeek
yipingwang22
6d 19h 28m 51s
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
36000
constant
1
32768
128
false
fsdp
1
true
true
true
true
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
true
-
true
0
32768
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
32768
true
8192
Crashed
adaptiveSeek
yipingwang22
1d 1h 18m 53s
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
3000
constant
1
24000
128
false
fsdp
1
true
true
true
true
Qwen/Qwen2.5-Math-1.5B
true
false
true
0
24000
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
24000
true
8192
Crashed
adaptiveSeek
yipingwang22
1d 6h 47m 20s
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
2000
constant
1
24000
128
false
fsdp
1
true
true
true
true
Qwen/Qwen2.5-Math-1.5B
true
false
true
0
24000
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
24000
true
8192
Crashed
adaptiveSeek
yipingwang22
1d 22h 37m 57s
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
2000
constant
1
24000
128
false
fsdp
1
true
true
true
true
Qwen/Qwen2.5-Math-1.5B
true
-
true
0
24000
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
24000
true
8192
Crashed
adaptiveSeek
yipingwang22
2d 8h 36m 12s
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
2000
constant
1
24000
128
false
fsdp
1
true
true
true
true
Qwen/Qwen2.5-Math-1.5B
true
-
true
0
24000
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
24000
true
8192
Crashed
adaptiveSeek
yipingwang22
15h 9m
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
2000
constant
1
24000
128
false
fsdp
1
true
true
true
true
Qwen/Qwen2.5-Math-1.5B
true
-
true
0
24000
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
24000
true
8192
Crashed
adaptiveSeek
yipingwang22
2d 18h 20s
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
4000
constant
1
24000
128
false
fsdp
1
true
true
true
true
Qwen/Qwen2.5-Math-1.5B
true
-
true
0
24000
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
24000
true
8192
Crashed
adaptiveSeek_3p_deepscaler_1.5b_baseline
yipingwang22
1d 15h 23m
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
4500
constant
1
24000
128
false
fsdp
1
true
true
true
true
Qwen/Qwen2.5-Math-1.5B
true
-
true
0
24000
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
24000
true
8192
Crashed
adaptiveSeek_3p_deepscaler_1.5b_baseline
yipingwang22
2d 5h 42m 31s
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
4500
constant
1
24000
128
false
fsdp
1
true
true
true
true
Qwen/Qwen2.5-Math-1.5B
true
-
true
0
24000
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
24000
true
8192
Finished
-
yipingwang22
3h 26m 8s
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
2000
constant
1
24000
128
false
fsdp
1
true
true
true
true
Qwen/Qwen2.5-Math-1.5B
true
false
true
0
24000
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
24000
true
8192
Crashed
adaptiveSeek
yipingwang22
5d 29m 18s
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
4000
constant
1
24000
128
false
fsdp
1
true
true
true
true
Qwen/Qwen2.5-Math-7B
true
-
true
0
24000
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
24000
true
8192
Crashed
adaptiveSeek
yipingwang22
4d 9h 18m 33s
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
2000
constant
1
24000
128
false
fsdp
1
true
true
true
true
Qwen/Qwen2.5-Math-7B
true
-
true
0
24000
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
24000
true
8192
Crashed
adaptiveSeek
yipingwang22
1d 9h 44m 34s
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
2000
constant
1
24000
128
false
fsdp
1
true
true
true
true
Qwen/Qwen2.5-Math-7B
true
-
true
0
24000
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
24000
true
8192
Crashed
adaptiveSeek
yipingwang22
1d 19h 52m 38s
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
4000
constant
1
24000
128
false
fsdp
1
true
true
true
true
Qwen/Qwen2.5-Math-7B
true
false
true
0
24000
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
24000
true
8192
Crashed
adaptiveSeek
yipingwang22
1d 14h 19m 45s
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
4000
constant
1
24000
128
false
fsdp
1
true
true
true
true
Qwen/Qwen2.5-Math-7B
true
false
true
0
24000
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
24000
true
8192
Crashed
adaptiveSeek
yipingwang22
6d 22h 16m 7s
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
2000
constant
1
24000
128
false
fsdp
1
true
true
true
true
Qwen/Qwen2.5-Math-7B
true
false
true
0
24000
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
24000
true
8192
Crashed
adaptiveSeek
yipingwang22
1d 9h 32m 29s
-
0.2
0.001
-1
false
false
false
0
1
0.001
low_var_kl
0.000001
0
4500
constant
1
24000
128
false
fsdp
1
true
true
true
true
Qwen/Qwen2.5-Math-7B
true
-
true
0
24000
true
1
true
true
bfloat16
true
true
true
0.7
false
dummy_dtensor
24000
true
8192
1-20
of 21