CoolFace
Modelpublic

sandeep123/grpo-qwen3-1.7b-nonthinking-entropy-2048-20260918

sourceHugging Faceupdated 8d agoView on Hugging Face
0likes
50 commits on main
60ece678d ago

Save verified benchmark grpo_entropy__epoch1/olympiad

sandeep123
7685cb88d ago

Save verified benchmark grpo_entropy__epoch2/olympiad

sandeep123
6a80ee78d ago

Save verified benchmark grpo_entropy__epoch3/olympiad

sandeep123
44c60658d ago

Save verified benchmark grpo_entropy__epoch3/aime25

sandeep123
ada19878d ago

Save verified benchmark grpo_entropy__epoch4/aime25

sandeep123
f98e5d08d ago

Save verified benchmark grpo_entropy__epoch2/aime25

sandeep123
b8252ea8d ago

Save verified benchmark grpo_entropy__epoch1/aime25

sandeep123
8b7d6518d ago

Save verified benchmark grpo_entropy__epoch2/aime24

sandeep123
54232508d ago

Save verified benchmark grpo_entropy__epoch3/aime24

sandeep123
2abd15e8d ago

Save verified benchmark grpo_entropy__epoch4/aime24

sandeep123
f327e448d ago

Save verified benchmark grpo_entropy__epoch4/olympiad

sandeep123
f976c4e8d ago

Save verified benchmark grpo_entropy__epoch1/aime24

sandeep123
99fb57a8d ago

Save verified benchmark grpo_entropy__epoch3/minerva

sandeep123
e98214e8d ago

Save verified benchmark grpo_entropy__epoch4/minerva

sandeep123
d13b30f8d ago

Save verified benchmark grpo_entropy__epoch2/minerva

sandeep123
9913a358d ago

Save verified benchmark grpo_entropy__epoch1/minerva

sandeep123
29084a18d ago

Save verified benchmark grpo_entropy__epoch3/math500

sandeep123
8482f378d ago

Save verified benchmark grpo_entropy__epoch1/math500

sandeep123
bc8ce4b8d ago

Save verified benchmark grpo_entropy__epoch2/math500

sandeep123
ae03be88d ago

Save verified benchmark grpo_entropy__epoch4/math500

sandeep123
b1a27838d ago

Archive verified training rollout update 126

sandeep123
5912e3c8d ago

Publish verified grpo_entropy LoRA update 128 (epoch 4)

sandeep123
e856f608d ago

Replace latest full resume with grpo_entropy epoch 4.0

sandeep123
2014b378d ago

Archive verified training rollout update 125

sandeep123
fef50f88d ago

Publish verified grpo_entropy LoRA update 127 (epoch 3.96875)

sandeep123
578927a8d ago

Archive verified training rollout update 124

sandeep123
f4bc99d8d ago

Publish verified grpo_entropy LoRA update 126 (epoch 3.9375)

sandeep123
0bad7268d ago

Archive verified training rollout update 123

sandeep123
eea20688d ago

Publish verified grpo_entropy LoRA update 125 (epoch 3.90625)

sandeep123
68f55bd8d ago

Archive verified training rollout update 122

sandeep123
3de736b8d ago

Publish verified grpo_entropy LoRA update 124 (epoch 3.875)

sandeep123
ebd895c8d ago

Publish verified grpo_entropy LoRA update 123 (epoch 3.84375)

sandeep123
767051f8d ago

Archive verified training rollout update 121

sandeep123
cb87cf98d ago

Publish verified grpo_entropy LoRA update 122 (epoch 3.8125)

sandeep123
e97cdc68d ago

Archive verified training rollout update 120

sandeep123
51fd3b38d ago

Publish verified grpo_entropy LoRA update 121 (epoch 3.78125)

sandeep123
ce97baf8d ago

Archive verified training rollout update 119

sandeep123
d5ced8d8d ago

Publish verified grpo_entropy LoRA update 120 (epoch 3.75)

sandeep123
ab876b18d ago

Archive verified training rollout update 118

sandeep123
ba8c3668d ago

Archive verified training rollout update 117

sandeep123
4450cb58d ago

Publish verified grpo_entropy LoRA update 119 (epoch 3.71875)

sandeep123
4b862bf8d ago

Publish verified grpo_entropy LoRA update 118 (epoch 3.6875)

sandeep123
ed36ae38d ago

Archive verified training rollout update 116

sandeep123
3300c3f8d ago

Archive verified training rollout update 115

sandeep123
96c2b588d ago

Publish verified grpo_entropy LoRA update 117 (epoch 3.65625)

sandeep123
187ce548d ago

Archive verified training rollout update 114

sandeep123
dca27af8d ago

Publish verified grpo_entropy LoRA update 116 (epoch 3.625)

sandeep123
cc546d58d ago

Publish verified grpo_entropy LoRA update 115 (epoch 3.59375)

sandeep123
13e53fa8d ago

Archive verified training rollout update 113

sandeep123
145af3e8d ago

Publish verified grpo_entropy LoRA update 114 (epoch 3.5625)

sandeep123