Update README.md

added epoch details for perp 51.8 model

README.md

@@ -36,7 +36,7 @@ Using Google Colab for training.
 
 Additional tutorial and source will be in https://github.com/gorkemgoknar in later stage.
 
-Current accuracy 28.9 %  , Perplexity : 86.71
+Current accuracy 33 %  , Perplexity : 51.88
 
 Models are available:
 
@@ -78,8 +78,8 @@ predicted_text = tokenizer.decode([predicted_index])
 print('input text:', text)
 print('predicted text:', predicted_text)
 
-# input text: Quem era Jim Henson? Jim Henson era um
-# predicted text:  homem
+# input text: 
+# predicted text:  
 
 ```
 
@@ -102,8 +102,7 @@ for i, sample_output in enumerate(sample_outputs):
     print(">> Generated text {}\n\n{}".format(i+1, tokenizer.decode(sample_output.tolist())))
 
 # >> Generated text
-# Quem era Jim Henson? Jim Henson era um executivo de televisão e diretor de um grande estúdio de cinema mudo chamado Selig,
-# depois que o diretor de cinema mudo Georges Seuray dirigiu vários filmes para a Columbia e o estúdio.    
+#    
 
 ```
 
@@ -121,12 +120,15 @@ Wikipedia Turkish article dump as of 28-10-2020
 
 ## Eval results
 
-epoch	train_loss	valid_loss	accuracy	perplexity	time
-0	6.922922	6.653488	0.148002	775.484253	2:26:41    
-1	4.799396	4.633522	0.277028	102.875755	3:03:38    
-2	4.610025	4.462641	0.289884	86.716248	2:34:50      
-
+| epoch	|train_loss	|valid_loss	|accuracy	|perplexity	|time   |
+| ----- | --------      |---------      | ----------    | ---------     | ----- |
+|0	|4.777015	|4.621834	|0.292547	|101.680367	|2:42:05|
+|1	|4.509412	|4.403999	|0.305574	|81.777267	|1:09:38|
+|2	|4.169529	|4.120755	|0.324908	|61.605747	|1:07:45|
+|3	|4.293973	|4.177899	|0.317211	|65.228653	|1:07:02|
+|4	|4.049848	|3.949103	|0.338347	|51.888783	|1:05:53|
 
+#Epoch 0 on Tesla T4, others on V100
 
 ```