sandeep123/stride-qwen3-1.7b-nonthinking-stabilized-2048-single_step-20260916
Save verified benchmark single_step__epoch4/aime25
Save verified benchmark single_step__epoch3/aime25
Save verified benchmark single_step__epoch2/aime25
Save verified benchmark single_step__epoch4/aime24
Save verified benchmark single_step__epoch1/aime25
Save verified benchmark single_step__epoch4/minerva
Save verified benchmark single_step__epoch3/aime24
Save verified benchmark single_step__epoch2/aime24
Save verified benchmark single_step__epoch1/aime24
Save verified benchmark single_step__epoch3/minerva
Save verified benchmark single_step__epoch4/math500
Save verified benchmark single_step__epoch2/minerva
Save verified benchmark single_step__epoch1/minerva
Save verified benchmark single_step__epoch3/math500
Save verified benchmark single_step__epoch2/math500
Save verified benchmark single_step__epoch4/olympiad
Save verified benchmark single_step__epoch1/math500
Save verified benchmark single_step__epoch3/olympiad
Save verified benchmark single_step__epoch2/olympiad
Save verified benchmark single_step__epoch1/olympiad
Save verified benchmark single_step/olympiad
Save verified benchmark single_step/minerva
Save verified benchmark single_step/math500
Save verified benchmark single_step/aime25
Save verified benchmark single_step/aime24
Save verified benchmark single_step/aime24
Archive verified training rollout update 126
Publish verified single_step LoRA update 128 (epoch 4)
Replace latest full resume with single_step epoch 4.0
Archive verified training rollout update 125
Publish verified single_step LoRA update 127 (epoch 3.96875)
Archive verified training rollout update 124
Publish verified single_step LoRA update 126 (epoch 3.9375)
Archive verified training rollout update 123
Publish verified single_step LoRA update 125 (epoch 3.90625)
Publish verified single_step LoRA update 124 (epoch 3.875)
Archive verified training rollout update 122
Archive verified training rollout update 121
Publish verified single_step LoRA update 123 (epoch 3.84375)
Publish verified single_step LoRA update 122 (epoch 3.8125)
Archive verified training rollout update 120
Archive verified training rollout update 119
Publish verified single_step LoRA update 121 (epoch 3.78125)
Publish verified single_step LoRA update 120 (epoch 3.75)
Archive verified training rollout update 118
Archive verified training rollout update 117
Publish verified single_step LoRA update 119 (epoch 3.71875)
Archive verified training rollout update 116
Publish verified single_step LoRA update 118 (epoch 3.6875)
Publish verified single_step LoRA update 117 (epoch 3.65625)
