Update README.md

README.md

@@ -156,8 +156,8 @@ Ethoric-10M was trained in two stages.
 
 | Stage | Tokens | Focus |
 |---|---|---|
-| 1. Stable | 15B | Broad mix of educational web text, synthetic textbooks, question-answer data and math |
-| 2. Cooldown | 4B | Learning rate decayed; mix shifted toward higher-quality math, QA and tutorial-style text |
+| Stable | 15B | Broad mix of educational web text, synthetic textbooks, question-answer data and math |
+| Cooldown | 4B | Learning rate decayed; mix shifted toward higher-quality math, QA and tutorial-style text |
 
 Training packs multiple documents into each 512-token sequence. Document masking keeps them separate: attention and Canon convolutions never reach across an EOS token.
 
@@ -181,9 +181,6 @@ The cooldown added new math sources such as FineMath, more question-answer and t
 
 † ELI5, GooAQ, FactBase-DCLM, Cosmopedia-v2, Natural Questions, Pretrain-Behaviors, UltraData-Math
 
-- **Tokenizer:** all data was tokenized with the model's 5,048-token BPE tokenizer, and 1% was held out for validation.
-- **Blending:** sources were blended per dataset using the weights above.
-
 ## Limitations
 
 - **Tiny model:** with 9.97M parameters and 256-dim hidden states, generations are often repetitive, incoherent or factually wrong. The model is a research artifact for studying small-scale LMs, not an assistant.