Skip to main content
ucalyptus
Projects
gsm-8k-16bit
Log in
Sign up
Overview
Workspace
Runs
Automat.
Sweeps
Reports
Artifacts
Ucalyptus's workspace
Personal workspace
Automated workspace
Changes are only visible to you.
Runs (17)
Name
(17 visualized)
qwen-2.5-3b_socratic_train_gsm8k.jsonl_1745457424
qwen-2.5-3b_socratic_train_gsm8k.jsonl_1745457424
qwen-2.5-0.5b_socratic_train_gsm8k.jsonl_1745456281
qwen-2.5-0.5b_socratic_train_gsm8k.jsonl_1745456281
qwen-2.5-0.5b_socratic_train_gsm8k.jsonl_1745452089
qwen-2.5-0.5b_socratic_train_gsm8k.jsonl_1745452089
qwen-2.5-32b_socratic_train_gsm8k.jsonl_1745437793
qwen-2.5-32b_socratic_train_gsm8k.jsonl_1745437793
qwen-2.5-3b_socratic_train_gsm8k.jsonl_1745437312
qwen-2.5-3b_socratic_train_gsm8k.jsonl_1745437312
qwen-2.5-7b_socratic_train_gsm8k.jsonl_1745437274
qwen-2.5-7b_socratic_train_gsm8k.jsonl_1745437274
qwen-2.5-0.5b_socratic_train_gsm8k.jsonl_1745437121
qwen-2.5-0.5b_socratic_train_gsm8k.jsonl_1745437121
qwen-2.5-1.5b_socratic_train_gsm8k.jsonl_1745362510
qwen-2.5-1.5b_socratic_train_gsm8k.jsonl_1745362510
phi-4-14b_socratic_train_gsm8k.jsonl_1745361026
phi-4-14b_socratic_train_gsm8k.jsonl_1745361026
qwen-2.5-14b_socratic_train_gsm8k.jsonl_1745358620
qwen-2.5-14b_socratic_train_gsm8k.jsonl_1745358620
qwen-2.5-32b_socratic_train_gsm8k.jsonl_1745356050
qwen-2.5-32b_socratic_train_gsm8k.jsonl_1745356050
qwen-2.5-3b_socratic_train_gsm8k.jsonl_1745354983
qwen-2.5-3b_socratic_train_gsm8k.jsonl_1745354983
qwen-2.5-3b_socratic_train_gsm8k.jsonl_1745349859
qwen-2.5-3b_socratic_train_gsm8k.jsonl_1745349859
qwen-2.5-1.5b_socratic_train_gsm8k.jsonl_1745348937
qwen-2.5-1.5b_socratic_train_gsm8k.jsonl_1745348937
qwen-2.5-7b_socratic_train_gsm8k.jsonl_1745347979
qwen-2.5-7b_socratic_train_gsm8k.jsonl_1745347979
qwen-2.5-14b_socratic_train_gsm8k.jsonl_1745346515
qwen-2.5-14b_socratic_train_gsm8k.jsonl_1745346515
qwen-2.5-1.5b_socratic_train_gsm8k.jsonl_1745345570
qwen-2.5-1.5b_socratic_train_gsm8k.jsonl_1745345570
1-17
of 17
Add panels
profiling
6
1-6 of 6
Tables
3
1-2 of 3
train
14
1-6 of 14
train/rewards/xml_format_reward
train/rewards/xml_format_reward
5k
10k
15k
20k
25k
Step
0.2
0.4
0.6
0.8
1
train/rewards/soft_reward
train/rewards/soft_reward
5k
10k
15k
20k
25k
Step
0.4
0.5
0.6
0.7
0.8
train/rewards/numeric_match_reward
train/rewards/numeric_match_reward
5k
10k
15k
20k
25k
Step
0.4
0.5
0.6
0.7
0.8
0.9
1
train/rewards/gsm_reward
train/rewards/gsm_reward
5k
10k
15k
20k
25k
Step
0.2
0.4
0.6
0.8
1
train/reward_std
train/reward_std
5k
10k
15k
20k
25k
Step
0
0.2
0.4
0.6
0.8
1
train/reward
train/reward
5k
10k
15k
20k
25k
Step
1
1.5
2
2.5
3
3.5
System
21
1-6 of 21
Add section