Update README.md

README.md

@@ -35,16 +35,17 @@ The model was trained on 3 corpora, which were hot-swapped during the training.
 
 
 <img src="figures/tloss_full.png"  width="900"/>
-Figure 1: Training loss.
+_Figure 1: Training loss._
 <img src="figures/tloss_closeup.png" width="900"/>
-Figure 2: Training loss closeup. We mark two hotswap places, where the training corpus #1 was switched for internal-corpus #2 and internal-corpus #2.1 respectively. 
+_Figure 2: Training loss closeup. We mark two hotswap places, where the training corpus #1 was switched for internal-corpus #2 and internal-corpus #2.1 respectively._
+
 Additionaly, we perform  two ablations:    
 
 - (a) After first hot swap, we continued training on the corpus #1 for a while.  
 - (b) On step 94,000, the training loss stopped decreasing, increased, and around step 120,000 (near hot swap #2) started decreasing again. To ablate whether this was an effect of hot-swap,
 - we resume training from step 93,000 using corpus #3. The optimizer states were reinitialized.  
 <img src="figures/vloss_closeup.png" width="900"/>
-Figure 3: Test loss closeup, testing performed on split of internal-corpus #1. See Figure 2 description for ablation explanation.
+_Figure 3: Test loss closeup, testing performed on split of internal-corpus #1. See Figure 2 description for ablation explanation._
 
 
 ## Training Method
@@ -52,7 +53,7 @@ Figure 3: Test loss closeup, testing performed on split of internal-corpus #1. S
 To transfer knowledge from English model to Czech, we developed a simple method that (i) aligns several tokens between two vocabularies and (ii) copies the embeddings from original language to new language.
 <img src="figures/tllama_test.png" width="900"/>
 
-Figure 4: Ablation: Test perplexity over the course of training for vocabulary swap method on TinyLLAMA. Our method (green curve) vs TinyLLAMA training from scratch (blue curve).
+_Figure 4: Ablation: Test perplexity over the course of training for vocabulary swap method on TinyLLAMA. Our method (green curve) vs TinyLLAMA training from scratch (blue curve)._
 
 The vocabulary swap was done the same way as our [Czech-GPT-2](https://huggingface.co/BUT-FIT/Czech-GPT-2-XL-133k) model (check it out for comprehensive description.)
 We managed to align 4,177 english tokens with corresponding czech tokens.