Update README.md

README.md

@@ -128,21 +128,21 @@ dataset = dataset.map(lambda x: {"formatted_chat": tokenizer.apply_chat_template
 #### Training Hyperparameters
 
 SFT parameters:
--num_train_epochs=1
--per_device_train_batch_size=2
--gradient_accumulation_steps=2
--gradient_checkpointing=True
--optim="adamw_torch_fused"
--learning_rate=2e-4
--max_grad_norm=0.3
--warmup_ratio=0.01
--lr_scheduler_type="cosine"
--bf16=True
+- num_train_epochs=1
+- per_device_train_batch_size=2
+- gradient_accumulation_steps=2
+- gradient_checkpointing=True
+- optim="adamw_torch_fused"
+- learning_rate=2e-4
+- max_grad_norm=0.3
+- warmup_ratio=0.01
+- lr_scheduler_type="cosine"
+- bf16=True
 
 LORA parameters:
--rank_dimension = 6
--lora_alpha = 8
--lora_dropout = 0.05
+- rank_dimension = 6
+- lora_alpha = 8
+- lora_dropout = 0.05