Update README.md

README.md

@@ -23,10 +23,9 @@ Trained using LLaMA-Factory with the config:
 ```
 max_seq_length = 6*1024
 
-lora_rank = 32
-lora_alpha = lora_rank * 2
-lora_target = ["q_proj", "k_proj", "v_proj", "o_proj",
-        "gate_proj", "up_proj", "down_proj"]
+lora_rank = 128
+lora_alpha = lora_rank
+lora_target = "all"
 
 args = dict(
   stage="sft",
@@ -38,25 +37,26 @@ args = dict(
   lora_target=lora_target,
   output_dir="qwen_distill_7b_lora",
   per_device_train_batch_size=1,
-  gradient_accumulation_steps=3,
+  gradient_accumulation_steps=4,
   lr_scheduler_type="cosine",
   logging_steps=1,
-  warmup_ratio=0.1,
-  save_steps=100,
+  warmup_ratio=0.05,
   learning_rate=1e-4,
   num_train_epochs=1.0,
-  max_grad_norm=1.0,
+  max_grad_norm=0.25,
   loraplus_lr_ratio=16.0,
   fp16=True,
   report_to="none",
   preprocessing_num_workers=16,
   cutoff_len=max_seq_length,
+  optim="paged_adamw_8bit"
 )
+
 ```
 
 System used:
 ```
-'You are a helpful assistant. Please reason step by step inside the tags <think> and </think>. Conclude with **Answer** and put your final answer within \\boxed{}.'
+'Please reason step by step inside the <think> and </think> tags, and put your final answer within \\boxed{}.'
 ```
 
 Custom template used in training:
@@ -89,6 +89,8 @@ register_template(
 )
 ```
 
+Every entry in the dataset starts with `<think>` and end its reasoning with `</think>`.
+
 In the dataset for variation, I randomly replaced the start of the string "Okay," with one of the following:
 ```
 starts = [