Bambi425sl's workspace
Runs
3
State
Notes
User
Tags
Created
Runtime
Sweep
actor_init_on_gpu
actor_learning_rate
actor_num_gpus_per_node
actor_num_nodes
adam_betas
adam_offload
add_think_token
advantage_estimator
apply_chat_template
aux_loss_coef
bf16
ckpt_path
colocate_actor_ref
colocate_critic_reward
critic_learning_rate
critic_num_gpus_per_node
critic_num_nodes
disable_fast_tokenizer
disable_trace_cache
enable_ema
enable_prefix_caching
enforce_eager
eps_clip
eval_steps
eval_temperature
eval_top_p
extra_eval_task
filter_samples_by_reward
flash_attn
freezing_actor_steps
gamma
generate_max_len
gradient_checkpointing
gradient_checkpointing_use_reentrant
init_kl_coef
input_key
l2
label_key
lambd
load_checkpoint
load_in_4bit
local_rank
logging_steps
lora_alpha
Finished
-
truman-yx-zuo
11h 15m 31s
-
false
5.0000e-7
4
1
[0.9,0.95]
true
0
group_norm
true
0
true
/mnt/public/zyx/outputs/AIME-TTT-Qwen2.5-Math-7B/0424/TTRL-group_norm/ckpt
true
false
0.000009
4
1
false
false
false
false
false
0.2
1
0
1
MATH-TTT,AMC-TTT
false
true
-1
1
3072
true
false
0
prompt
0
answer
1
false
false
-1
1
16
Finished
-
truman-yx-zuo
11h 16m 1s
-
false
5.0000e-7
4
1
[0.9,0.95]
true
0
group_norm
true
0
true
/mnt/public/zyx/code/ttrl_code/outputs/AIME-TTT-Qwen2.5-Math-7B/0423/TTRL-group_norm/ckpt
true
false
0.000009
4
1
false
false
false
false
false
0.2
1
0
1
AMC-TTT,MATH-TTT
false
true
-1
1
3072
true
false
0
prompt
0
answer
1
false
false
-1
1
16
Finished
-
truman-yx-zuo
11h 40m 27s
-
false
5.0000e-7
4
1
[0.9,0.95]
true
0
group_norm
true
0
true
../final_outputs/AIME-TTT-Qwen2.5-Math-7B/0423/TTRL-group_norm/ckpt
true
false
0.000009
4
1
false
false
false
false
false
0.2
1
0
1
AIME25-TTT,AMC-TTT,MATH-TTT
false
true
-1
1
3072
true
false
0
prompt
0
answer
1
false
false
-1
1
16
1-3
of 3