Skip to main content
ucalyptus
Projects
gsm_hard
Log in
Sign up
Project
Workspace
Runs
Automat.
Sweeps
Reports
Artifacts
Ucalyptus's workspace
Personal workspace
Automated workspace
Changes are only visible to you.
Runs
12
Name
12 visualized
qwen-2.5-3b/train_gsm_hard.jsonl/
qwen-2.5-3b/train_gsm_hard.jsonl/
qwen-2.5-3b/train_gsm_hard.jsonl/
qwen-2.5-3b/train_gsm_hard.jsonl/
phi-4-14b/train_gsm_hard.jsonl/
phi-4-14b/train_gsm_hard.jsonl/
qwen-2.5-0.5b/train_gsm_hard.jsonl/
qwen-2.5-0.5b/train_gsm_hard.jsonl/
qwen-2.5-1.5b/train_gsm_hard.jsonl/
qwen-2.5-1.5b/train_gsm_hard.jsonl/
llama-3.2-3b/train_gsm_hard.jsonl/
llama-3.2-3b/train_gsm_hard.jsonl/
qwen-2.5-7b/train_gsm_hard.jsonl/
qwen-2.5-7b/train_gsm_hard.jsonl/
phi-4-14b/train_gsm_hard.jsonl/
phi-4-14b/train_gsm_hard.jsonl/
llama-3.1-8b/train_gsm_hard.jsonl/
llama-3.1-8b/train_gsm_hard.jsonl/
llama-3.2-3b/train_gsm_hard.jsonl/
llama-3.2-3b/train_gsm_hard.jsonl/
qwen-2.5-0.5b/train_gsm_hard.jsonl/
qwen-2.5-0.5b/train_gsm_hard.jsonl/
qwen-2.5-3b/train_gsm_hard.jsonl/
qwen-2.5-3b/train_gsm_hard.jsonl/
1-12
of 12
Previous
Next
train/reward_std
train/reward_std
Showing first 10 runs
50
100
150
200
250
train/global_step
0
0.5
1
1.5
2
qwen-2.5-3b/train_gsm_hard.jsonl/
qwen-2.5-3b/train_gsm_hard.jsonl/
phi-4-14b/train_gsm_hard.jsonl/
qwen-2.5-0.5b/train_gsm_hard.jsonl/
qwen-2.5-1.5b/train_gsm_hard.jsonl/
llama-3.2-3b/train_gsm_hard.jsonl/
qwen-2.5-7b/train_gsm_hard.jsonl/
phi-4-14b/train_gsm_hard.jsonl/
llama-3.1-8b/train_gsm_hard.jsonl/
llama-3.2-3b/train_gsm_hard.jsonl/