Update README.md

README.md

@@ -36,19 +36,19 @@ print(result[0]['generated_text'])
 ```
 
 ## Training Details
-lora_r: 16
-lora_alpha: 8
+lora_r: 16  
+lora_alpha: 8  
 lora_dropout: 0.05
-target_modules: q, k, v, o, gate_proj, down_proj, up_proj, lm_head
-weight_decay: 0
-optmizer: paged_adamw_32bit
-lr: 1e-4
-lr_scheduler: cosine
-max_seq_len: 4096
-batch_size: 4
-max_grad_norm: 0.5
-warmup_ratio: 0.05
-num_epochs: 1
+target_modules: q, k, v, o, gate_proj, down_proj, up_proj, lm_head  
+weight_decay: 0  
+optmizer: paged_adamw_32bit  
+lr: 1e-4  
+lr_scheduler: cosine  
+max_seq_len: 4096  
+batch_size: 4  
+max_grad_norm: 0.5  
+warmup_ratio: 0.05  
+num_epochs: 1  
 
 Training was performed on the python subset of the ds-coder-instruct dataset.