Update README.md

Correct the training process explanation (reversed)

README.md

@@ -46,14 +46,14 @@ for name, param in model.named_parameters():
 
 Our strategy involved a selective freeze of model parameters. Specifically, we kept most parameters of the base model unchanged while focusing on enhancing the Korean language capabilities. Through our experiments, we discovered:
 
-1. Freezing the `lm_head` layer for existing tokens is crucial to maintain overall performance.
-2. Unfreezing the `embed_tokens` layer for existing tokens actually boosts performance.
+1. Freezing the `embed_tokens` layer for existing tokens is crucial to maintain overall performance.
+2. Unfreezing the `lm_head` layer for existing tokens actually boosts performance.
 
 As a result, we froze the internal layers and the first 32,000 `embed_tokens`, directing our training efforts on a rich mix of Korean and multi-lingual corpora. This balanced approach has notably improved the model’s proficiency in Korean, without compromising its original language capabilities.
 
 ### Usage and Limitations
 
-Keep in mind, this model hasn't been fine-tuned with instruction-based training. While it excels in Korean language tasks, we advise careful consideration and further training for specific applications.
+Keep in mind that this model hasn't been fine-tuned with instruction-based training. While it excels in Korean language tasks, we advise careful consideration and further training for specific applications.
 
 ### Training Details
 
@@ -73,13 +73,13 @@ Our model’s training was comprehensive and diverse:
 
     3. **Manual Tokenizer Construction:** We then built the target tokenizer, focusing on these new Korean tokens.
 
-    4. **Frequency Analysis:** Using target tokenizer, we processed a 100GB Korean corpus to count each token's frequency.
+    4. **Frequency Analysis:** Using the target tokenizer, we processed a 100GB Korean corpus to count each token's frequency.
 
     5. **Refinement of Token List:** We removed tokens appearing less than 6,000 times, ensuring to secure enough tokens to train models later.
 
-    6. **Inclusion of Single-Letter Characters:** Counted missing Korean single-letter characters and added them to the target tokenizer that appearing more than 6,000 times.
+    6. **Inclusion of Single-Letter Characters:** Counted missing Korean single-letter characters and added them to the target tokenizer that appeared more than 6,000 times.
 
-    7. **Iterative Refinement:** We repeated steps 2 to 6 until there are no tokens to drop or add.
+    7. **Iterative Refinement:** We repeated steps 2 to 6 until there were no tokens to drop or add.
 
     8. **Training Bias Towards New Tokens:** Our training data was biased to include more texts with new tokens, for effective learning.