GXPO-math-seed-42
Checkpoints from run 'gxpo_qwen_3B_k_3_shutoff_trajectory_aware_hendry' for iso-BP comparison.
Updated • 23Note run=gxpo_qwen_3B_k_3_shutoff_trajectory_aware_hendrycks_math_seed42_20260411_114108 | checkpoint=best_checkpoint
swapnil7777/gxpo-gxpo-qwen-3b-k-3-shutoff-trajectory-aware-hendrycks-math-seed42-20260411-114108-ch-8f7a9687
Updated • 23Note run=gxpo_qwen_3B_k_3_shutoff_trajectory_aware_hendrycks_math_seed42_20260411_114108 | checkpoint=checkpoint-184
swapnil7777/gxpo-gxpo-qwen-3b-k-3-shutoff-trajectory-aware-hendrycks-math-seed42-20260411-114108-ch-2393e580
Updated • 22Note run=gxpo_qwen_3B_k_3_shutoff_trajectory_aware_hendrycks_math_seed42_20260411_114108 | checkpoint=checkpoint-362
swapnil7777/gxpo-gxpo-qwen-3b-k-3-shutoff-trajectory-aware-hendrycks-math-seed42-20260411-114108-ch-9c4ebc27
Updated • 21Note run=gxpo_qwen_3B_k_3_shutoff_trajectory_aware_hendrycks_math_seed42_20260411_114108 | checkpoint=checkpoint-364
swapnil7777/gxpo-gxpo-qwen-3b-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260411-114637-be-52f7c6e5
Updated • 22Note run=gxpo_qwen_3B_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260411_114637 | checkpoint=best_checkpoint
swapnil7777/gxpo-gxpo-qwen-3b-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260411-114637-bp-2c933d0a
UpdatedNote run=gxpo_qwen_3B_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260411_114637 | checkpoint=bp_budget_350
swapnil7777/gxpo-gxpo-qwen-3b-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260411-114637-bp-3a0c7752
UpdatedNote run=gxpo_qwen_3B_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260411_114637 | checkpoint=bp_budget_502
swapnil7777/gxpo-gxpo-qwen-3b-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260411-114637-bp-2bfcd1bb
UpdatedNote run=gxpo_qwen_3B_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260411_114637 | checkpoint=bp_budget_528
swapnil7777/gxpo-gxpo-qwen-3b-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260411-114637-ch-1a0ad791
Updated • 23Note run=gxpo_qwen_3B_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260411_114637 | checkpoint=checkpoint-316
swapnil7777/gxpo-gxpo-qwen-3b-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260411-114637-ch-87c4901b
Updated • 22Note run=gxpo_qwen_3B_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260411_114637 | checkpoint=checkpoint-350
swapnil7777/gxpo-gxpo-qwen-3b-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260411-114637-ch-33191273
Updated • 21Note run=gxpo_qwen_3B_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260411_114637 | checkpoint=checkpoint-352
swapnil7777/gxpo-gxpo-qwen-3b-k-10-shutoff-trajectory-aware-hendrycks-math-seed42-20260412-025004-b-1c30da4f
Updated • 20Note run=gxpo_qwen_3B_k_10_shutoff_trajectory_aware_hendrycks_math_seed42_20260412_025004 | checkpoint=best_checkpoint
swapnil7777/gxpo-gxpo-qwen-3b-k-10-shutoff-trajectory-aware-hendrycks-math-seed42-20260412-025004-b-52f6fd45
UpdatedNote run=gxpo_qwen_3B_k_10_shutoff_trajectory_aware_hendrycks_math_seed42_20260412_025004 | checkpoint=bp_budget_350
swapnil7777/gxpo-gxpo-qwen-3b-k-10-shutoff-trajectory-aware-hendrycks-math-seed42-20260412-025004-c-5e541317
Updated • 18Note run=gxpo_qwen_3B_k_10_shutoff_trajectory_aware_hendrycks_math_seed42_20260412_025004 | checkpoint=checkpoint-356
swapnil7777/gxpo-gxpo-qwen-3b-k-10-shutoff-trajectory-aware-hendrycks-math-seed42-20260412-025004-c-e6e7661f
Updated • 21Note run=gxpo_qwen_3B_k_10_shutoff_trajectory_aware_hendrycks_math_seed42_20260412_025004 | checkpoint=checkpoint-374
swapnil7777/gxpo-gxpo-qwen-3b-k-10-shutoff-trajectory-aware-hendrycks-math-seed42-20260412-025004-c-bd2bde43
Updated • 19Note run=gxpo_qwen_3B_k_10_shutoff_trajectory_aware_hendrycks_math_seed42_20260412_025004 | checkpoint=checkpoint-375