Update README.md

README.md

@@ -15,9 +15,16 @@ pipeline_tag: text-generation
 ---
 # OPT-125M finetuned Portuguese 
 
-Fine-tuning the [OPT-125M](https://huggingface.co/facebook/opt-125m) model on a reduced corpus of MC4-Portuguese with approximately 300M tokens.
+Fine-tuning the [OPT-125M](https://huggingface.co/facebook/opt-125m) model on a reduced corpus of mc4-Portuguese with approximately 300M tokens.
 
-In this training a sequence length of 512 tokens was used, batch of 32 for 2 epochs.
+###### Hyper-parameters
+
+
+- learning_rate = 5e-5
+- batch_size = 32
+- warmup = 500
+- seq_length = 512
+- num_train_epochs = 2.0
 
 With an A100 with 40GB of RAM, the training took around 3 hours