Skip to main content
ucalyptus
Projects
grpo-april
Workspace
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
146
Name
146 visualized
qwen-2.5-3b/test_gsm_symbolic_formatted.jsonl/
qwen-2.5-3b/test_gsm_symbolic_formatted.jsonl/
llama-3.2-3b/test_gsm_symbolic_formatted.jsonl/
llama-3.2-3b/test_gsm_symbolic_formatted.jsonl/
qwen-2.5-0.5b/test_gsm_symbolic_formatted.jsonl/
qwen-2.5-0.5b/test_gsm_symbolic_formatted.jsonl/
llama-3.2-1b/test_gsm_symbolic_formatted.jsonl/
llama-3.2-1b/test_gsm_symbolic_formatted.jsonl/
qwen-2.5-1.5b/test_gsm_symbolic_formatted.jsonl/
qwen-2.5-1.5b/test_gsm_symbolic_formatted.jsonl/
phi-4-14b/test_gsm_symbolic_formatted.jsonl/
phi-4-14b/test_gsm_symbolic_formatted.jsonl/
llama-3.2-1b/test_gsm_symbolic_formatted.jsonl/
llama-3.2-1b/test_gsm_symbolic_formatted.jsonl/
qwen-2.5-0.5b/test_gsm_symbolic_formatted.jsonl/
qwen-2.5-0.5b/test_gsm_symbolic_formatted.jsonl/
llama-3.1-8b/test_gsm_symbolic_formatted.jsonl/
llama-3.1-8b/test_gsm_symbolic_formatted.jsonl/
qwen-2.5-7b/test_gsm_symbolic_formatted.jsonl/
qwen-2.5-7b/test_gsm_symbolic_formatted.jsonl/
qwen-2.5-7b/file-5fb436eb-210e-47c1-95a7-736cbac3e5ac.jsonl/
qwen-2.5-7b/file-5fb436eb-210e-47c1-95a7-736cbac3e5ac.jsonl/
qwen-2.5-7b/file-5fb436eb-210e-47c1-95a7-736cbac3e5ac.jsonl/
qwen-2.5-7b/file-5fb436eb-210e-47c1-95a7-736cbac3e5ac.jsonl/
qwen-2.5-7b/file-5fb436eb-210e-47c1-95a7-736cbac3e5ac.jsonl/
qwen-2.5-7b/file-5fb436eb-210e-47c1-95a7-736cbac3e5ac.jsonl/
qwen-2.5-7b/file-5fb436eb-210e-47c1-95a7-736cbac3e5ac.jsonl/
qwen-2.5-7b/file-5fb436eb-210e-47c1-95a7-736cbac3e5ac.jsonl/
qwen-2.5-7b/file-5fb436eb-210e-47c1-95a7-736cbac3e5ac.jsonl/
qwen-2.5-7b/file-5fb436eb-210e-47c1-95a7-736cbac3e5ac.jsonl/
qwen-2.5-1.5b/file-b8294709-8811-4daf-a428-3ebcdad2f245.jsonl/
qwen-2.5-1.5b/file-b8294709-8811-4daf-a428-3ebcdad2f245.jsonl/
llama-3.1-8b/file-a0a24a76-633e-4b4d-a81c-63507ba389e8.jsonl/
llama-3.1-8b/file-a0a24a76-633e-4b4d-a81c-63507ba389e8.jsonl/
llama-3.1-8b/file-eb3b6be1-fa96-4be0-89c0-0c30dd44c4a0.jsonl/
llama-3.1-8b/file-eb3b6be1-fa96-4be0-89c0-0c30dd44c4a0.jsonl/
llama-3.2-1b/file-8cf52c9d-6d0d-448a-979f-844a010f7659.jsonl/
llama-3.2-1b/file-8cf52c9d-6d0d-448a-979f-844a010f7659.jsonl/
qwen-2.5-3b/file-aa9b1322-9e13-4ae9-a62a-2ff1f1bcbb25.jsonl/
qwen-2.5-3b/file-aa9b1322-9e13-4ae9-a62a-2ff1f1bcbb25.jsonl/
1-20
of 146
train/rewards/xml_format_reward
train/rewards/xml_format_reward
200
400
600
800
1k
1.2k
1.4k
Step
0
0.2
0.4
0.6
0.8
1
llama-3.2-3b/test_gsm_symbolic_formatted.jsonl/
qwen-2.5-1.5b/test_gsm_symbolic_formatted.jsonl/
phi-4-14b/test_gsm_symbolic_formatted.jsonl/
llama-3.2-1b/test_gsm_symbolic_formatted.jsonl/
qwen-2.5-0.5b/test_gsm_symbolic_formatted.jsonl/
llama-3.1-8b/test_gsm_symbolic_formatted.jsonl/
qwen-2.5-7b/test_gsm_symbolic_formatted.jsonl/
qwen-2.5-7b/file-ac04a62a-5c4d-4814-9640-377c9eff88d9.jsonl/
qwen-2.5-7b/file-b0b926d9-739e-4bd5-a9db-c615ff59ee97.jsonl/
Previous
Next