Update README.md

README.md

@@ -68,6 +68,8 @@ probabilities = torch.nn.functional.softmax(logits, dim=-1)
 ## Training data
 
 The **segment-nt-30kb** model was trained on all human chromosomes except for chromosomes 20 and 21, kept as test set, and chromosome 22, used as a validation set.
+During training, sequences are randomly sampled in the genome with associated annotations. However, we keep the sequences in the validation and test set fixed by 
+using a sliding window of length 30,000 over the chromosomes 20 and 21. The validation set was used to monitor training and for early stopping.
 
 ## Training procedure
 
@@ -81,7 +83,7 @@ The DNA sequences are tokenized using the Nucleotide Transformer Tokenizer, whic
 
 ### Training
 
-The model was trained on a DGXH100 on a total of 23B tokens. The model was trained on 3kb, 10kb, 20kb and finally 30kb sequences, at each time with an effective batch size of 256 sequences. 
+The model was trained on a DGXH100 node with 8 GPUs on a total of 23B tokens for 3 days. The model was trained on 3kb, 10kb, 20kb and finally 30kb sequences, at each time with an effective batch size of 256 sequences. 
 
 
 ### Architecture