0.5B Block Attention Residuals checkpoint trained on 9,999,745,024 tokens.
-
Attention-residual blocks (n): 8
-
Routing rank (r): 64
-
Reported final validation loss: 2.9480
-
Final checkpoint step: 38146
-
Training tokens processed: 9999745024
-
Artifact: final_model.pt
-
Artifact size: 2472428351 bytes
-
Artifact LFS SHA256: fc15a8eca5672645df0ce2f80ae65d8f2a0129224d9ccd85968793d100262146
-
The validation value is the owner-recorded full-sweep result. The original upload did not include a structured evaluation JSON.
