Update README.md

README.md

@@ -62,16 +62,16 @@ print(outputs[0]["generated_text"])
 ### Training hyper-parameters
 The following hyperparameters were used during training:
 
-learning_rate: 4.0e-5
-train_batch_size: 2
-seed: 42
-packing: false
-distributed_type: deepspeed-zero-3
-num_devices: 8
-gradient_accumulation_steps: 8
-total_train_batch_size: 16
-optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-lr_scheduler_type: cosine_with_min_lr
-min_lr_rate: 0.1
-lr_scheduler_warmup_ratio: 0.03
-num_epochs: 10.0
+- learning_rate: 4.0e-5
+- train_batch_size: 2
+- seed: 42
+- packing: false
+- distributed_type: deepspeed-zero-3
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine_with_min_lr
+- min_lr_rate: 0.1
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 10.0