GRPO
Checkpoints from run 'gxpo_qwen-1.5B_0.5_k_3_shutoff_trajectory_aware_' for iso-BP comparison.
Updated • 22Note run=gxpo_qwen-1.5B_0.5_k_3_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032210 | checkpoint=best_checkpoint
swapnil7777/grpo-gxpo-qwen-1-5b-0-5-k-3-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-032-4cbc72ce
UpdatedNote run=gxpo_qwen-1.5B_0.5_k_3_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032210 | checkpoint=bp_budget_350
swapnil7777/grpo-gxpo-qwen-1-5b-0-5-k-3-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-032-83c076ba
UpdatedNote run=gxpo_qwen-1.5B_0.5_k_3_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032210 | checkpoint=bp_budget_502
swapnil7777/grpo-gxpo-qwen-1-5b-0-5-k-3-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-032-8aa9de5a
UpdatedNote run=gxpo_qwen-1.5B_0.5_k_3_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032210 | checkpoint=bp_budget_528
swapnil7777/grpo-gxpo-qwen-1-5b-0-5-k-3-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-032-6df2443e
Updated • 26Note run=gxpo_qwen-1.5B_0.5_k_3_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032210 | checkpoint=checkpoint-360
swapnil7777/grpo-gxpo-qwen-1-5b-0-5-k-3-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-032-137b06c8
Updated • 18Note run=gxpo_qwen-1.5B_0.5_k_3_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032210 | checkpoint=checkpoint-380
swapnil7777/grpo-gxpo-qwen-1-5b-0-5-k-3-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-032-cd522c47
Updated • 24Note run=gxpo_qwen-1.5B_0.5_k_3_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032210 | checkpoint=checkpoint-396
swapnil7777/grpo-gxpo-qwen-1-5b-0-5-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-032-0eade1e7
Updated • 23Note run=gxpo_qwen-1.5B_0.5_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032446 | checkpoint=best_checkpoint
swapnil7777/grpo-gxpo-qwen-1-5b-0-5-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-032-b6e102a5
UpdatedNote run=gxpo_qwen-1.5B_0.5_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032446 | checkpoint=bp_budget_350
swapnil7777/grpo-gxpo-qwen-1-5b-0-5-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-032-a2870974
UpdatedNote run=gxpo_qwen-1.5B_0.5_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032446 | checkpoint=bp_budget_502
swapnil7777/grpo-gxpo-qwen-1-5b-0-5-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-032-1faa21c8
UpdatedNote run=gxpo_qwen-1.5B_0.5_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032446 | checkpoint=bp_budget_528
swapnil7777/grpo-gxpo-qwen-1-5b-0-5-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-032-53e46c11
Updated • 24Note run=gxpo_qwen-1.5B_0.5_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032446 | checkpoint=checkpoint-360
swapnil7777/grpo-gxpo-qwen-1-5b-0-5-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-032-1648c7b4
Updated • 23Note run=gxpo_qwen-1.5B_0.5_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032446 | checkpoint=checkpoint-380
swapnil7777/grpo-gxpo-qwen-1-5b-0-5-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-032-6c2559d4
Updated • 24Note run=gxpo_qwen-1.5B_0.5_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032446 | checkpoint=checkpoint-396
swapnil7777/grpo-gxpo-qwen-1-5b-1-k-10-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-0329-ccd3ce4d
Updated • 23Note run=gxpo_qwen-1.5B_1_k_10_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032946 | checkpoint=best_checkpoint
swapnil7777/grpo-gxpo-qwen-1-5b-1-k-10-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-0329-825c9b31
UpdatedNote run=gxpo_qwen-1.5B_1_k_10_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032946 | checkpoint=bp_budget_350
swapnil7777/grpo-gxpo-qwen-1-5b-1-k-10-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-0329-bafccdd7
UpdatedNote run=gxpo_qwen-1.5B_1_k_10_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032946 | checkpoint=bp_budget_502
swapnil7777/grpo-gxpo-qwen-1-5b-1-k-10-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-0329-99db5444
UpdatedNote run=gxpo_qwen-1.5B_1_k_10_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032946 | checkpoint=bp_budget_528
swapnil7777/grpo-gxpo-qwen-1-5b-1-k-10-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-0329-dd493e0f
Updated • 23Note run=gxpo_qwen-1.5B_1_k_10_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032946 | checkpoint=checkpoint-360
swapnil7777/grpo-gxpo-qwen-1-5b-1-k-10-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-0329-1ae047fb
Updated • 23Note run=gxpo_qwen-1.5B_1_k_10_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032946 | checkpoint=checkpoint-380
swapnil7777/grpo-gxpo-qwen-1-5b-1-k-10-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-0329-709d78d5
Updated • 16Note run=gxpo_qwen-1.5B_1_k_10_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032946 | checkpoint=checkpoint-396
swapnil7777/grpo-gxpo-qwen-1-5b-1-k-10-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-0628-acf89781
Updated • 25Note run=gxpo_qwen-1.5B_1_k_10_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_062829 | checkpoint=best_checkpoint
swapnil7777/grpo-gxpo-qwen-1-5b-1-k-10-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-0628-e36332a8
UpdatedNote run=gxpo_qwen-1.5B_1_k_10_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_062829 | checkpoint=bp_budget_350
swapnil7777/grpo-gxpo-qwen-1-5b-1-k-10-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-0628-2481a322
UpdatedNote run=gxpo_qwen-1.5B_1_k_10_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_062829 | checkpoint=bp_budget_502
swapnil7777/grpo-gxpo-qwen-1-5b-1-k-10-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-0628-a5e79e8f
UpdatedNote run=gxpo_qwen-1.5B_1_k_10_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_062829 | checkpoint=bp_budget_528
swapnil7777/grpo-gxpo-qwen-1-5b-1-k-10-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-0628-a5eff752
Updated • 25Note run=gxpo_qwen-1.5B_1_k_10_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_062829 | checkpoint=checkpoint-360
swapnil7777/grpo-gxpo-qwen-1-5b-1-k-10-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-0628-9f5e9756
Updated • 23Note run=gxpo_qwen-1.5B_1_k_10_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_062829 | checkpoint=checkpoint-380
swapnil7777/grpo-gxpo-qwen-1-5b-1-k-10-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-0628-913b5ee3
Updated • 21Note run=gxpo_qwen-1.5B_1_k_10_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_062829 | checkpoint=checkpoint-396