Skip to main content
ucalyptus
Projects
unsloth-dr-grpo-march
Workspace
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
158
Name
158 visualized
llama-3.2-3b/file-f041abb1-3ebd-422a-9fd6-46183b95ab59.jsonl/
llama-3.2-3b/file-f041abb1-3ebd-422a-9fd6-46183b95ab59.jsonl/
llama-3.2-1b/file-1d332eee-5cd7-4f30-bebb-88bbfa925bc0.jsonl/
llama-3.2-1b/file-1d332eee-5cd7-4f30-bebb-88bbfa925bc0.jsonl/
qwen-2.5-0.5b/file-1095d352-ce58-458c-bfe0-b2df4c8f1ea1.jsonl/
qwen-2.5-0.5b/file-1095d352-ce58-458c-bfe0-b2df4c8f1ea1.jsonl/
qwen-2.5-0.5b/file-c8584a63-48b2-40f6-9f70-c7c7e110aff3.jsonl/
qwen-2.5-0.5b/file-c8584a63-48b2-40f6-9f70-c7c7e110aff3.jsonl/
qwen-2.5-0.5b/file-7e8db655-fd73-46ee-a9ae-a38aa9c38edc.jsonl/
qwen-2.5-0.5b/file-7e8db655-fd73-46ee-a9ae-a38aa9c38edc.jsonl/
llama-3.1-8b/file-9165d45f-c06e-4bbd-b325-4f70f10064c4.jsonl/
llama-3.1-8b/file-9165d45f-c06e-4bbd-b325-4f70f10064c4.jsonl/
llama-3.2-1b/file-61189174-5099-4528-9534-ca56b787b4c6.jsonl/
llama-3.2-1b/file-61189174-5099-4528-9534-ca56b787b4c6.jsonl/
llama-3.2-1b/file-02ce40e0-8e19-4cbe-8566-efbeb5a8fcae.jsonl/
llama-3.2-1b/file-02ce40e0-8e19-4cbe-8566-efbeb5a8fcae.jsonl/
qwen-2.5-7b/file-e4c638f0-49a5-4fdd-a8f3-b1bf9d911eea.jsonl/
qwen-2.5-7b/file-e4c638f0-49a5-4fdd-a8f3-b1bf9d911eea.jsonl/
qwen-2.5-3b/file-4fc21354-a798-41a5-8863-542b4b7e8bd1.jsonl/
qwen-2.5-3b/file-4fc21354-a798-41a5-8863-542b4b7e8bd1.jsonl/
qwen-2.5-1.5b/file-1095d352-ce58-458c-bfe0-b2df4c8f1ea1.jsonl/
qwen-2.5-1.5b/file-1095d352-ce58-458c-bfe0-b2df4c8f1ea1.jsonl/
llama-3.1-8b/file-c0644438-bc37-4c9e-b280-e31e802ad2f3.jsonl/
llama-3.1-8b/file-c0644438-bc37-4c9e-b280-e31e802ad2f3.jsonl/
llama-3.2-1b/file-50c328de-0bb2-420e-9409-53ed9aa3502c.jsonl/
llama-3.2-1b/file-50c328de-0bb2-420e-9409-53ed9aa3502c.jsonl/
llama-3.2-3b/file-61a3b6f0-e285-453f-a3a7-3b6909f806f9.jsonl/
llama-3.2-3b/file-61a3b6f0-e285-453f-a3a7-3b6909f806f9.jsonl/
qwen-2.5-7b/file-50c328de-0bb2-420e-9409-53ed9aa3502c.jsonl/
qwen-2.5-7b/file-50c328de-0bb2-420e-9409-53ed9aa3502c.jsonl/
phi-4-14b/file-ab6f190a-b747-41d0-ab36-f2b97e768248.jsonl/
phi-4-14b/file-ab6f190a-b747-41d0-ab36-f2b97e768248.jsonl/
llama-3.2-1b/file-374c6bab-2102-40b7-b6b4-848a7c3cb7eb.jsonl/
llama-3.2-1b/file-374c6bab-2102-40b7-b6b4-848a7c3cb7eb.jsonl/
llama-3.2-3b/file-37d5c9b9-c2de-4953-ad06-b9ff3d4c70ac.jsonl/
llama-3.2-3b/file-37d5c9b9-c2de-4953-ad06-b9ff3d4c70ac.jsonl/
llama-3.1-8b/file-b41f618e-d357-4554-bd71-fe18b40a7fe2.jsonl/
llama-3.1-8b/file-b41f618e-d357-4554-bd71-fe18b40a7fe2.jsonl/
qwen-2.5-7b/file-62682faf-7e8c-4b99-b3d3-cca84d9f3a8d.jsonl/
qwen-2.5-7b/file-62682faf-7e8c-4b99-b3d3-cca84d9f3a8d.jsonl/
1-20
of 158
Previous
Next
profiling/Time taken: UnslothGRPOTrainer.code_syntax_reward
profiling/Time taken: UnslothGRPOTrainer.code_syntax_reward
200
400
600
800
1k
1.2k
Step
0.002
0.004
0.006
0.008
0.01
llama-3.2-3b/file-c6df36e0-2fd1-4c8b-84fe-7855eade4b45.jsonl/
qwen-2.5-3b/file-c6df36e0-2fd1-4c8b-84fe-7855eade4b45.jsonl/
llama-3.1-8b/file-c6df36e0-2fd1-4c8b-84fe-7855eade4b45.jsonl/
qwen-2.5-1.5b/file-c6df36e0-2fd1-4c8b-84fe-7855eade4b45.jsonl/
qwen-2.5-3b/file-a766c888-c9e2-4fdd-8f5f-8940cfeec050.jsonl/
llama-3.2-1b/file-c6df36e0-2fd1-4c8b-84fe-7855eade4b45.jsonl/
qwen-2.5-7b/file-e6a30acf-988a-4182-bf79-f6ed698f280b.jsonl/
llama-3.2-1b/file-c2127f1b-69fc-48cc-a374-45b379db856c.jsonl/
qwen-2.5-3b/file-74bd175b-b2dd-489f-b3d3-1d74454a21d1.jsonl/