Chrisjina's workspace
Runs
59
Name
19 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
actor_init_on_gpu
actor_learning_rate
adam_betas
adam_offload
advantage_estimator
apply_chat_template
aux_loss_coef
bf16
ckpt_path
disable_ds_ckpt
disable_fast_tokenizer
enable_ema
eps_clip
eval_steps
flash_attn
freezing_actor_steps
gamma
generate_max_len
gradient_checkpointing
gradient_checkpointing_use_reentrant
init_kl_coef
input_key
input_template
l2
lambd
load_checkpoint
load_in_4bit
local_rank
logging_steps
lora_alpha
lora_dropout
lora_rank
lr_warmup_ratio
max_ckpt_mem
max_ckpt_num
max_epochs
max_norm
max_samples
micro_rollout_batch_size
micro_train_batch_size
n_samples_per_prompt
normalize_reward
num_episodes
overlap_comm
Finished
-
chrisjina
29s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph6/openrlhf/PURE_PRMVR_Qwen2.5_Base_0225010831/checkpoints
true
false
false
0.2
-1
true
-
1
2048
true
false
0.001
question
{}
Please reason step by step with steps separated by "
", and put your final answer within \boxed{{}}.
0
1
false
false
0
1
16
0
0
0.03
100000000
15
1
1
1000000
4
2
4
false
2000
false
Finished
-
chrisjina
11h 41m 17s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph6/openrlhf/PURE_VR_deepseek_0220003518/checkpoints
true
false
false
0.2
-1
true
-
1
8192
true
false
0.001
problem
{}
Please reason step by step with steps separated by "
", and put your final answer within \boxed{{}}. <think>
0
1
false
false
0
1
16
0
0
0.03
100000000
15
1
1
1000000
2
2
4
false
1000000
false
Finished
-
chrisjina
11h 40m 48s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph6/openrlhf/PURE_PRMVR_deepseek_0220002730/checkpoints
true
false
false
0.2
-1
true
-
1
8192
true
false
0.001
problem
{}
Please reason step by step with steps separated by "
", and put your final answer within \boxed{{}}. <think>
0
1
false
false
0
1
16
0
0
0.03
100000000
15
1
1
1000000
2
2
4
false
1000000
false
Finished
-
chrisjina
16h 24m 18s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph6/openrlhf/PURE_VR_0213181413/checkpoints
true
false
false
0.2
-1
true
-
1
2048
true
false
0.001
question
{}
Please reason step by step with steps separated by "
", and put your final answer within \boxed{{}}.
0
1
false
false
0
1
16
0
0
0.03
100000000
15
1
1
1000000
4
2
4
false
2000
false
Finished
-
chrisjina
15h 11m 48s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph6/openrlhf/PURE_PRM_0213164214/checkpoints
true
false
false
0.2
-1
true
-
1
2048
true
false
0.001
question
{}
Please reason step by step with steps separated by "
", and put your final answer within \boxed{{}}.
0
1
false
false
0
1
16
0
0
0.03
100000000
15
1
1
1000000
4
2
4
false
2000
false
Finished
-
chrisjina
19h 37m 9s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph6/openrlhf/ray_0212213219/checkpoints
true
false
false
0.2
-1
true
-
1
2048
true
false
0.001
question
{}
Please reason step by step with steps separated by "
", and put your final answer within \boxed{{}}.
0
1
false
false
0
1
16
0
0
0.03
100000000
15
1
1
1000000
4
2
4
false
2000
false
Finished
-
chrisjina
1d 1h 24m
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph5/openrlhf/ray_0211232954/checkpoints
true
false
false
0.2
-1
true
-
1
2048
true
false
0.001
question
{}
Please reason step by step with steps separated by "
", and put your final answer within \boxed{{}}.
0
1
false
false
0
1
16
0
0
0.03
100000000
15
1
1
1000000
4
2
4
false
2000
false
Finished
-
chrisjina
21h 15m 17s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph5/openrlhf/ray_0211183003/checkpoints
true
false
false
0.2
-1
true
-
1
2048
true
false
0.001
question
{}
Please reason step by step with steps separated by "
", and put your final answer within \boxed{{}}.
0
1
false
false
0
1
16
0
0
0.03
100000000
15
1
1
1000000
4
2
4
false
2000
false
Finished
-
chrisjina
2d 13h 56m 2s
-
false
3.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph5/openrlhf/ray_debug_0208200231/checkpoints
true
false
false
0.2
-1
true
-
1
2048
true
false
0.001
question
-
0
1
false
false
0
1
16
0
0
0.03
100000000
15
1
1
1000000
4
2
4
false
2000
false
Finished
-
chrisjina
1d 53m 37s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph5/openrlhf/ray_debug_0208195759/checkpoints
true
false
false
0.2
-1
true
-
1
2048
true
false
0.001
question
-
0
1
false
false
0
1
16
0
0
0.03
100000000
15
1
1
1000000
4
2
4
false
2000
false
Finished
-
chrisjina
1d 23h 22m 18s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph5/openrlhf/ray_debug_0207185325/checkpoints
true
false
false
0.2
-1
true
-
1
2048
true
false
0.001
question
-
0
1
false
false
0
1
16
0
0
0.03
100000000
15
1
1
1000000
4
2
4
false
2000
false
Finished
-
chrisjina
20h 51m 28s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph5/openrlhf/debug_0206225026/checkpoints
true
false
false
0.2
-1
true
-1
1
2048
true
false
0.001
question
{}
Please reason step by step with steps separated by "
", and put your final answer within \boxed{{}}.
0
1
false
false
0
1
16
0
0
0.03
100000000
10
2
1
1000000
4
2
4
false
20
false
Finished
-
chrisjina
15h 42m 32s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph5/openrlhf/debug_0205181944/checkpoints
true
false
false
0.2
-1
true
-1
1
2048
true
false
0.01
question
{}
Please reason step by step with steps separated by "
", and put your final answer within \boxed{{}}.
0
1
false
false
0
1
16
0
0
0.03
100000000
10
2
1
1000000
4
2
4
false
20
false
Finished
-
chrisjina
22h 56m 53s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph5/openrlhf/debug_0205181838/checkpoints
true
false
false
0.2
-1
true
-1
1
2048
true
false
0.001
question
{}
Please reason step by step with steps separated by "
", and put your final answer within \boxed{{}}.
0
1
false
false
0
1
16
0
0
0.03
100000000
10
2
1
1000000
4
2
4
false
20
false
Finished
-
chrisjina
15h 41m 34s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph5/openrlhf/debug_0205181539/checkpoints
true
false
false
0.2
-1
true
-1
1
2048
true
false
0.001
question
{}
Please reason step by step with steps separated by "
", and put your final answer within \boxed{{}}.
0
1
false
false
0
1
16
0
0
0.03
100000000
10
2
1
1000000
4
2
4
false
20
false
Finished
-
chrisjina
1d 2h 22m 41s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph5/openrlhf/debug_0205181211/checkpoints
true
false
false
0.2
-1
true
-1
1
2048
true
false
0.001
question
{}
Please reason step by step with steps separated by "
", and put your final answer within \boxed{{}}.
0
1
false
false
0
1
16
0
0
0.03
100000000
10
2
1
1000000
4
2
4
false
20
false
Finished
-
chrisjina
1d 9h 22m 24s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph5/openrlhf/ray_debug_0205094305/checkpoints
true
false
false
0.2
-1
true
-
1
2048
true
false
0.001
question
-
0
1
false
false
0
1
16
0
0
0.03
100000000
10
1
1
1000000
4
2
4
false
20
false
Finished
-
chrisjina
15h 53m 59s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph4/openrlhf/ray_debug_0204133630/checkpoints
true
false
false
0.2
-1
true
-
1
2048
true
false
0.001
question
-
0
1
false
false
0
1
16
0
0
0.03
100000000
10
1
1
1000000
4
2
4
false
20
false
Finished
-
chrisjina
15h 53m 13s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph4/openrlhf/ray_debug_0204133255/checkpoints
true
false
false
0.2
-1
true
-
1
2048
true
false
0.001
question
-
0
1
false
false
0
1
16
0
0
0.03
100000000
3
2
1
1000000
4
2
4
false
20
false
Finished
-
chrisjina
22h 33m 8s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph4/openrlhf/ray_debug_0204074614/checkpoints
true
false
false
0.2
-1
true
-
1
2048
true
false
0.001
question
-
0
1
false
false
0
1
16
0
0
0.03
100000000
3
1
1
1000000
4
2
4
false
20
false
Finished
-
chrisjina
23h 54m 38s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph4/openrlhf/debug_0201121738/checkpoints
false
false
false
0.2
-1
true
-1
1
2048
true
false
0.0001
question
{}
Please reason step by step with steps separated by "
", and put your final answer within \boxed{{}}.
0
1
false
false
0
1
16
0
0
0.03
100000000
3
2
1
1000000
4
2
4
false
1
false
Finished
-
chrisjina
1d 7h 48m 7s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph3/openrlhf/debug_0201001727/checkpoints
false
false
false
0.2
-1
true
-1
1
2048
true
false
0.001
question
{}
Please reason step by step with steps separated by "
", and put your final answer within \boxed{{}}.
0
1
false
false
0
1
16
0
0
0.03
100000000
3
2
1
1000000
4
2
4
false
1
false
Finished
-
chrisjina
19h 24m 57s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph4/openrlhf/debug_0131201923/checkpoints
false
false
false
0.2
-1
true
-1
1
2048
true
false
0.001
question
{}
Please reason step by step with steps separated by "
", and put your final answer within \boxed{{}}.
0
1
false
false
0
1
16
0
0
0.03
100000000
3
2
1
1000000
4
2
4
false
1
false
Finished
-
chrisjina
5h 32m 7s
-
false
5.0000e-7
[0.9,0.95]
true
rloo
false
0
true
/mnt/petrelfs/chengjie/ceph3/openrlhf/debug_0131093328/checkpoints
false
false
false
0.2
-1
true
-1
1
2048
true
false
0.01
question
{}
Please reason step by step with steps separated by "
", and put your final answer within \boxed{{}}.
0
1
false
false
0
1
16
0
0
0.03
100000000
3
2
1
1000000
4
2
4
false
1
false
1-24
of 24