Johnny1024/bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_bottom20_nogap_randret-maxsteps2 4B • Updated Apr 30 • 6
Johnny1024/bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_bottom20_nogap-maxsteps200-resp2 4B • Updated Apr 30 • 7
Johnny1024/bs16-k5-lr5e-7-ema0.01-eopd0.8-olmo-7b-think-sciknoweval_material_bottom20_nogap 7B • Updated Apr 29 • 1
Johnny1024/bs16-k5-lr5e-7-ema0.01-eopd0.8-olmo-7b-think-sciknoweval_chem_bottom20_nogap 7B • Updated Apr 29 • 3
Johnny1024/bs16-k5-lr5e-7-ema0.01-eopd0.8-olmo-7b-think-sciknoweval_bio_bottom20_nogap 7B • Updated Apr 29 • 2
Johnny1024/bs16-k20-lr5e-7-ema0-eopd0.8-qwen3-4b-think-mmlu_pro_train10k_bottom20-s150 4B • Updated Apr 28 • 5
Johnny1024/GRPO-edu_feedback-train16-n8-cosine-Qwen-Qwen2.5-3B-Instruct-biochem-mix20-3b-lr5e-6-maxstep100 3B • Updated Apr 25 • 2
Johnny1024/bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_physics_bottom20_nogap_xdomrandret-ma 4B • Updated Apr 25 • 2
Johnny1024/GRPO-edu_feedback-train16-n8-lr1e-6-cosine-Qwen-Qwen3-4B-Instruct-2507-bio_oly-qwn3-4B-lr5e-6-ma 4B • Updated Apr 25 • 2
Johnny1024/GRPO-edu_feedback-train16-n8-lr1e-6-cosine-Qwen-Qwen2.5-3B-Instruct-maxstep100 3B • Updated Apr 25 • 2
Johnny1024/bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_physics_bottom20_nogap_randret-maxste 4B • Updated Apr 20 • 1
Johnny1024/bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_physics_middle20_nogap-maxsteps150 4B • Updated Apr 20 • 2
Johnny1024/bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_physics_sensitive20pct_nogap-maxsteps 4B • Updated Apr 20 • 1
Johnny1024/bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_bio_bottom20_nogap_randret-maxsteps15 4B • Updated Apr 20 • 1
Johnny1024/bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_bio_middle20_nogap-maxsteps150 4B • Updated Apr 20 • 2
Johnny1024/bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_bio_sensitive20pct_nogap-maxsteps150 4B • Updated Apr 20 • 1
Johnny1024/bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_middle20_nogap-maxsteps150 4B • Updated Apr 20 • 2
Johnny1024/bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_sensitive20pct_nogap-maxsteps150 4B • Updated Apr 20