Update model: SFT step 1825, loss=4.3889

Update model: SFT step 1525, loss=4.4235

Update model: SFT step 1050, loss=4.6154

Update model: SFT step 1025, loss=4.9765

Update model: SFT step 850, loss=5.0193

Update model: SFT step 675, loss=5.3019

Verified raw state_dict (weights_only=True compatible)

Raw state_dict from SFT step 200

Stage 3 SFT checkpoint (step ~115, in-progress training)

Upload pruned Aetheris (536M params, 80K vocab, 25.7% smaller)

Upload Aetheris model (Stage 2 best, 722M params, loss=2.73)