Upload docs/TRAINING_LOG_1B.md with huggingface_hub

docs/TRAINING_LOG_1B.md

@@ -130,6 +130,50 @@ OUTPUT:  Population Population Population Population Population Population Popul
 - Re-probe after further loss drop (targets ~25 and ~20).
 
 
+
+
+## Unified merge probe — loss ≈ 30 (2026-08-16 05:28 UTC)
+
+**Live shard losses at merge time**
+
+| GPU | Tokens | Loss |
+|-----|--------|------|
+| 0 | 127.9M | 38.6 |
+| 1 | 135.7M | **30.0** |
+| 2 | 136.4M | 32.3 |
+| 3 | 136.0M | 33.5 |
+
+**Artifact:** `FRACTUS_1B_MERGED_LIVE.pt` (4.66 GB) — mean of 4 live shard checkpoints  
+**Load:** 424 / 440 tensors  
+
+### Raw generation outputs (unified)
+
+```
+PROMPT: The meaning of life is
+OUTPUT:  uphe uphe uphe uphe uphe uphe uphe uphe uphe uphe ...
+
+PROMPT: Hello, my name is
+OUTPUT:  Colorado Colorado Colorado Colorado Colorado Colorado ...
+
+PROMPT: In mathematics, a continuous system
+OUTPUT:  Fate Fate Fate Fate Fate Fate Fate Fate Fate Fate ...
+
+PROMPT: Fractus thinks
+OUTPUT:  Population Population Population Population Population ...
+
+PROMPT: Once upon a time
+OUTPUT:  commands commands commands commands commands commands ...
+```
+
+### Reading
+
+- GPU1 crossed **loss 30**.
+- Unified checkpoint still produces **word-level tokens** in repetition loops (not char noise).
+- New lexical items vs earlier probe (e.g. `Fate`, `commands`) alongside recurring ones (`Colorado`, `Population`).
+- Not coherent sentences yet. Pipeline + merge path confirmed again.
+- Next probes planned near loss ~25 and ~20.
+
+
 ## Operational policy
 
 - Do not stop the 4-GPU digestion while loss is still monotonically improving.