swapnil7777/sfpo-sfpo-qwen-3b-k-5-hendrycks-math-seed42-20260410-100741-best-checkpoint Updated Apr 11 • 4
swapnil7777/sfpo-sfpo-qwen-3b-k-3-hendrycks-math-seed42-20260410-100614-checkpoint-396 Updated Apr 11 • 3
swapnil7777/sfpo-sfpo-qwen-3b-k-3-hendrycks-math-seed42-20260410-100614-checkpoint-394 Updated Apr 11 • 2
swapnil7777/sfpo-sfpo-qwen-3b-k-3-hendrycks-math-seed42-20260410-100614-checkpoint-228 Updated Apr 11 • 4
swapnil7777/sfpo-sfpo-qwen-3b-k-3-hendrycks-math-seed42-20260410-100614-best-checkpoint Updated Apr 11 • 2
swapnil7777/sfpo-gxpo-qwen-3b-k-5-hendrycks-math-seed42-20260410-184131-checkpoint-234 Updated Apr 11 • 5
swapnil7777/sfpo-gxpo-qwen-3b-k-5-hendrycks-math-seed42-20260410-184131-checkpoint-232 Updated Apr 11 • 3
swapnil7777/sfpo-gxpo-qwen-3b-k-5-hendrycks-math-seed42-20260410-184131-checkpoint-228 Updated Apr 11 • 2
swapnil7777/sfpo-gxpo-qwen-3b-k-5-hendrycks-math-seed42-20260410-184131-best-checkpoint Updated Apr 11 • 2