Merge branch 'main' of https://osredm.com/p04798526/LLaMA-Factory-Mirror

results/inference/Baichuan2-7B/Baichuan2_predict_1.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: baichuan-inc/baichuan-7B
+model_name_or_path: ../../llm/baichuan
 
 ### method
 do_predict: true

results/inference/Baichuan2-7B/Baichuan2_predict_1_single.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: baichuan-inc/baichuan-7B
+model_name_or_path: ../../llm/baichuan
 
 ### method
 do_predict: true

results/inference/Baichuan2-7B/Baichuan2_predict_2.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: baichuan-inc/baichuan-7B
+model_name_or_path: ../../llm/baichuan
 
 ### method
 do_predict: true

results/inference/Baichuan2-7B/Baichuan2_predict_2_single.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: baichuan-inc/baichuan-7B
+model_name_or_path: ../../llm/baichuan
 
 ### method
 do_predict: true

results/inference/Baichuan2-7B/Baichuan2_predict_3.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: baichuan-inc/baichuan-7B
+model_name_or_path: ../../llm/baichuan
 
 ### method
 do_predict: true

results/inference/Baichuan2-7B/Baichuan2_predict_3_single.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: baichuan-inc/baichuan-7B
+model_name_or_path: ../../llm/baichuan
 
 ### method
 do_predict: true

results/inference/Qwen-7B/Qwen_predict_1.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: qwen/Qwen-7B
+model_name_or_path: ../../llm/qwen
 
 ### method
 do_predict: true

results/inference/Qwen-7B/Qwen_predict_1_single.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: qwen/Qwen-7B
+model_name_or_path: ../../llm/qwen
 
 ### method
 do_predict: true

results/inference/Qwen-7B/Qwen_predict_2.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: qwen/Qwen-7B
+model_name_or_path: ../../llm/qwen
 
 ### method
 do_predict: true

results/inference/Qwen-7B/Qwen_predict_2_single.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: qwen/Qwen-7B
+model_name_or_path: ../../llm/qwen
 
 ### method
 do_predict: true

results/inference/Qwen-7B/Qwen_predict_3.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: qwen/Qwen-7B
+model_name_or_path: ../../llm/qwen
 
 ### method
 do_predict: true

results/inference/Qwen-7B/Qwen_predict_3_single.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: qwen/Qwen-7B
+model_name_or_path: ../../llm/qwen
 
 ### method
 do_predict: true

results/lora_sft/Baichuan2-7B/Baichuan2_lora_sft_1.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: baichuan-inc/baichuan-7B
+model_name_or_path: ../../llm/baichuan
 
 ### method
 stage: sft

results/lora_sft/Baichuan2-7B/Baichuan2_lora_sft_1_single.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: baichuan-inc/baichuan-7B
+model_name_or_path: ../../llm/baichuan
 
 ### method
 stage: sft

results/lora_sft/Baichuan2-7B/Baichuan2_lora_sft_2.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: baichuan-inc/baichuan-7B
+model_name_or_path: ../../llm/baichuan
 
 ### method
 stage: sft

results/lora_sft/Baichuan2-7B/Baichuan2_lora_sft_2_single.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: baichuan-inc/baichuan-7B
+model_name_or_path: ../../llm/baichuan
 
 ### method
 stage: sft

results/lora_sft/Baichuan2-7B/Baichuan2_lora_sft_3.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: baichuan-inc/baichuan-7B
+model_name_or_path: ../../llm/baichuan
 
 ### method
 stage: sft

results/lora_sft/Baichuan2-7B/Baichuan2_lora_sft_3_single.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: baichuan-inc/baichuan-7B
+model_name_or_path: ../../llm/baichuan
 
 ### method
 stage: sft

results/lora_sft/Qwen-7B/Qwen_lora_sft_1.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: qwen/Qwen-7B
+model_name_or_path: ../../llm/qwen
 
 ### method
 stage: sft

results/lora_sft/Qwen-7B/Qwen_lora_sft_1_single.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: qwen/Qwen-7B
+model_name_or_path: ../../llm/qwen
 
 ### method
 stage: sft

results/lora_sft/Qwen-7B/Qwen_lora_sft_2.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: qwen/Qwen-7B
+model_name_or_path: ../../llm/qwen
 
 ### method
 stage: sft

results/lora_sft/Qwen-7B/Qwen_lora_sft_2_single.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: qwen/Qwen-7B
+model_name_or_path: ../../llm/qwen
 
 ### method
 stage: sft

results/lora_sft/Qwen-7B/Qwen_lora_sft_3.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: qwen/Qwen-7B
+model_name_or_path: ../../llm/qwen
 
 ### method
 stage: sft

results/lora_sft/Qwen-7B/Qwen_lora_sft_3_single.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: qwen/Qwen-7B
+model_name_or_path: ../../llm/qwen
 
 ### method
 stage: sft

src/gpu_status.py

@@ -26,7 +26,7 @@ def main():
             cur_time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()),
             all_gpu_status = all_gpu_status
         )
-        with open("./results/gpu_status.json", "a", encoding="utf-8") as f:
+        with open("./results/gpu_status_0821.json", "a", encoding="utf-8") as f:
             f.write(json.dumps(logs) + "\n")
         print(logs)
         time.sleep(60)