Update README.md

README.md

@@ -109,29 +109,29 @@ Use the code below to get started with the model.
 
 - **Training regime:**
 
-max_seq_length = 2000
-trainer = SFTTrainer(
-    model = model,
-    tokenizer = tokenizer,
-    train_dataset = train,
-    dataset_text_field = "text",
-    max_seq_length = max_seq_length,
-    dataset_num_proc = 2,
-    packing = False, # Can make training 5x faster for short sequences.
-    args = TrainingArguments(
-        per_device_train_batch_size = 2,
-        gradient_accumulation_steps = 4,
-        warmup_steps = 5,
-        max_steps = 50,
-        learning_rate = 2e-4,
-        fp16 = not is_bfloat16_supported(),
-        bf16 = is_bfloat16_supported(),
-        logging_steps = 1,
-        optim = "adamw_8bit",
-        weight_decay = 0.01,
-        lr_scheduler_type = "linear",
-        seed = 3407,
-        output_dir = "outputs",
+```max_seq_length = 2000
+``` trainer = SFTTrainer(
+```     model = model,
+```     tokenizer = tokenizer,
+```     train_dataset = train,
+```     dataset_text_field = "text",
+```     max_seq_length = max_seq_length,
+```     dataset_num_proc = 2,
+```     packing = False, # Can make training 5x faster for short sequences.
+```     args = TrainingArguments(
+```         per_device_train_batch_size = 2,
+```         gradient_accumulation_steps = 4,
+ ```        warmup_steps = 5,
+      ```    max_steps = 50,
+      ```   learning_rate = 2e-4,
+      ```   fp16 = not is_bfloat16_supported(),
+      ```   bf16 = is_bfloat16_supported(),
+      ```   logging_steps = 1,
+      ```   optim = "adamw_8bit",
+      ```   weight_decay = 0.01,
+      ```   lr_scheduler_type = "linear",
+      ```   seed = 3407,
+      ```   output_dir = "outputs",
     ),
 )
 #### Speeds, Sizes, Times [optional]