shunxing1234
commited on
Commit
•
c0687c5
1
Parent(s):
8effa6a
Update README.md
Browse files
README.md
CHANGED
@@ -87,11 +87,11 @@ bash dist_trigger_docker.sh hostfile Aquila-pretrain.yaml aquila-7b [实验名]
|
|
87 |
```
|
88 |
接下来会输出下列信息,注意`NODES_NUM`应该与节点数相等,`LOGFILE`是模型运行的日志文件;The following information will be output. Note that `NODES_NUM` should be equal to the number of nodes, and `LOGFILE` is the log file for the model run.
|
89 |
|
90 |
-
![Screenshot](
|
91 |
|
92 |
成功训练之前能看到如下信息(具体参数可能不同); Before successful training, you may see the following information with parameters that may differ:
|
93 |
|
94 |
-
![Screenshot](
|
95 |
|
96 |
### 2. 可监督微调/Supervised Fine-tuning(SFT)
|
97 |
#### Step 1: 修改参数/Modify Parameters
|
@@ -108,11 +108,11 @@ bash dist_trigger_docker.sh hostfile aquila-sft.yaml aquila-7b [实验名]
|
|
108 |
```
|
109 |
接下来会输出下列信息,注意`NODES_NUM`应该与节点数相等,`LOGFILE`是模型运行的日志文件;The following information will be output. Note that `NODES_NUM` should be equal to the number of nodes, and `LOGFILE` is the log file for the model run.
|
110 |
|
111 |
-
![Screenshot](
|
112 |
|
113 |
成功训练之前能看到如下信息(具体参数可能不同); Before successful training, you may see the following information with parameters that may differ:
|
114 |
|
115 |
-
![Screenshot](
|
116 |
|
117 |
### 3. 推理/Inference
|
118 |
|
|
|
87 |
```
|
88 |
接下来会输出下列信息,注意`NODES_NUM`应该与节点数相等,`LOGFILE`是模型运行的日志文件;The following information will be output. Note that `NODES_NUM` should be equal to the number of nodes, and `LOGFILE` is the log file for the model run.
|
89 |
|
90 |
+
![Screenshot](./info.jpg)
|
91 |
|
92 |
成功训练之前能看到如下信息(具体参数可能不同); Before successful training, you may see the following information with parameters that may differ:
|
93 |
|
94 |
+
![Screenshot](./info2.jpg)
|
95 |
|
96 |
### 2. 可监督微调/Supervised Fine-tuning(SFT)
|
97 |
#### Step 1: 修改参数/Modify Parameters
|
|
|
108 |
```
|
109 |
接下来会输出下列信息,注意`NODES_NUM`应该与节点数相等,`LOGFILE`是模型运行的日志文件;The following information will be output. Note that `NODES_NUM` should be equal to the number of nodes, and `LOGFILE` is the log file for the model run.
|
110 |
|
111 |
+
![Screenshot](./info.jpg)
|
112 |
|
113 |
成功训练之前能看到如下信息(具体参数可能不同); Before successful training, you may see the following information with parameters that may differ:
|
114 |
|
115 |
+
![Screenshot](./info2.jpg)
|
116 |
|
117 |
### 3. 推理/Inference
|
118 |
|