Skip to main content
jonhue
Projects
TTCs
Workspace
Log in
Sign up
Project
Workspace
Runs
Automat.
Sweeps
Reports
Artifacts
Jonhue's workspace
Personal workspace
Automated workspace
Changes are only visible to you.
Runs
48
Name
48 visualized
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_aime24_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_aime24_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_math500_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_math500_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_aime25_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_aime25_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_math500_500000-Qwen_Qwen3-8B-grpo-params_False_random_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_math500_500000-Qwen_Qwen3-8B-grpo-params_False_random_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_aime25_500000-Qwen_Qwen3-8B-grpo-params_False_random_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_aime25_500000-Qwen_Qwen3-8B-grpo-params_False_random_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_aime24_500000-Qwen_Qwen3-8B-grpo-params_False_random_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_aime24_500000-Qwen_Qwen3-8B-grpo-params_False_random_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_aime25_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_True_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_aime25_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_True_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_math500_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_True_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_math500_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_True_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_aime24_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_True_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_aime24_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_True_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_Idavidrein_gpqa-D_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_True_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_Idavidrein_gpqa-D_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_True_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_Idavidrein_gpqa-D_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_Idavidrein_gpqa-D_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_Idavidrein_gpqa-D_500000-Qwen_Qwen3-8B-grpo-params_False_random_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_Idavidrein_gpqa-D_500000-Qwen_Qwen3-8B-grpo-params_False_random_False_1000_1000_2_42
final_experiments_individual_aime-lasgroup_ttt_reasoning_dataset_math-ai_aime25_0_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments_individual_aime-lasgroup_ttt_reasoning_dataset_math-ai_aime25_0_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments_individual_aime-lasgroup_ttt_reasoning_dataset_math-ai_aime25_1_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments_individual_aime-lasgroup_ttt_reasoning_dataset_math-ai_aime25_1_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments_individual_aime-lasgroup_ttt_reasoning_dataset_math-ai_aime25_10_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments_individual_aime-lasgroup_ttt_reasoning_dataset_math-ai_aime25_10_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments_individual_aime-lasgroup_ttt_reasoning_dataset_math-ai_aime25_11_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments_individual_aime-lasgroup_ttt_reasoning_dataset_math-ai_aime25_11_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments_individual_aime-lasgroup_ttt_reasoning_dataset_math-ai_aime25_12_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments_individual_aime-lasgroup_ttt_reasoning_dataset_math-ai_aime25_12_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments_individual_aime-lasgroup_ttt_reasoning_dataset_math-ai_aime25_13_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments_individual_aime-lasgroup_ttt_reasoning_dataset_math-ai_aime25_13_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments_individual_aime-lasgroup_ttt_reasoning_dataset_math-ai_aime25_14_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments_individual_aime-lasgroup_ttt_reasoning_dataset_math-ai_aime25_14_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments_individual_aime-lasgroup_ttt_reasoning_dataset_math-ai_aime25_15_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments_individual_aime-lasgroup_ttt_reasoning_dataset_math-ai_aime25_15_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
1-20
of 48
actor/pg_clipfrac_lower
actor/pg_clipfrac_lower
Showing first 10 runs
50
100
150
200
250
Step
0
0.00002
0.00004
0.00006
0.00008
0.0001
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_aime24_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_math500_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_aime25_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_math500_500000-Qwen_Qwen3-8B-grpo-params_False_random_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_aime25_500000-Qwen_Qwen3-8B-grpo-params_False_random_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_aime24_500000-Qwen_Qwen3-8B-grpo-params_False_random_False_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_aime25_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_True_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_math500_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_True_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_math-ai_aime24_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_True_1000_1000_2_42
final_experiments-lasgroup_ttt_reasoning_dataset_Idavidrein_gpqa-D_500000-Qwen_Qwen3-8B-grpo-params_False_vtl_True_1000_1000_2_42
Previous
Next