Skip to main content
accuracy-maker
Projects
Llama3.2-1B-GRPO
Workspace
Log in
Sign up
Overview
Workspace
Runs
Automat.
Sweeps
Reports
Artifacts
Accuracy-maker's workspace
Personal workspace
Automated workspace
Changes are only visible to you.
Runs
2
Name
2 visualized
Llama-3.2-1B-GRPO-gsm8k-2
Llama-3.2-1B-GRPO-gsm8k-2
Llama-3.2-1B-GRPO-gsm8k
Llama-3.2-1B-GRPO-gsm8k
1-2
of 2
train/rewards/int_reward_func
train/rewards/int_reward_func
200
400
600
800
1k
1.2k
1.4k
train/global_step
0
0.1
0.2
0.3
0.4
0.5
Llama-3.2-1B-GRPO-gsm8k-2
Llama-3.2-1B-GRPO-gsm8k
Previous
Next