Update README.md

README.md

@@ -100,3 +100,19 @@ At the time of release, MedGENIE-fid-flan-t5-base-medqa is a new lightweight SOT
 | LLaMa-2 <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small>                 | &empty;            | 0-shot                    | 13B             | 31.1                          |
 | GPT-NeoX <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small>               | &empty;            | 0-shot                    | 20B             | 26.9                          |    
 
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- num_devices: 1
+- n_context: 5
+- per_gpu_batch_size: 1
+- accumulation_steps: 4 
+- total_steps: 
+- eval_freq: 
+- optimizer: adamw 
+- scheduler: linear
+- weight_decay: 0.01
+- warmup_steps: 
+- text_maxlength: 1024
+