Update EmberNet Stage 2 Epoch 3/5 | loss 4.1517 | step 1875

README.md

@@ -13,7 +13,7 @@ pipeline_tag: image-text-to-text
 
 # EmberNet — BitNet b1.58 MoE VLM
 
-> **Status:** Stage 2/2, Epoch 2/5, Loss 4.3319
+> **Status:** Stage 2/2, Epoch 3/5, Loss 4.1517
 
 EmberNet is a tiny but capable Vision-Language Model built for edge deployment
 and domain-expert reasoning.  It combines a frozen **SigLIP** vision backbone
@@ -32,11 +32,11 @@ preserving strong visual understanding across 8 specialised domains.
 | **Total parameters** | 840.8 M |
 | **Trainable parameters** | 723.3 M |
 | **Active parameters / forward** | ~235.4 M (top-2 routing) |
-| **Carbon footprint** | 0.4225 kg CO₂eq |
+| **Carbon footprint** | 0.6390 kg CO₂eq |
 | **Training stage** | Stage 2/2 — Expert SFT |
-| **Epoch** | 2/5 |
-| **Best loss** | 4.3319 |
-| **Last updated** | 2026-03-08 02:21 UTC |
+| **Epoch** | 3/5 |
+| **Best loss** | 4.1517 |
+| **Last updated** | 2026-03-08 06:05 UTC |
 
 ---
 

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3ab3eb6ca4b3c43ad582f0da89aab0095693ccd519cf5c3a999cdfbec4ef70b
+oid sha256:cf4d2c2a29d7ccced5560c8744219073d735148f900f301966665f363b5038ef
 size 3397346561