update to conform to json format

Author: Tong Li

applications/ColossalChat/coati/distributed/README.md

@@ -135,7 +135,7 @@ Each data sample in the training or evaluation `.jsonl` file should follow this
 | ---------------- | --------------------------------------- | ----------------- |
 | `--model`        | Model path or identifier                | `/path/to/model` |
 | `--dataset`      | Path to training `.jsonl`               | `/path/to/train_data.jsonl`      |
-| `--eval-dataset` | JSON of task\:eval\_dataset\_path pairs | `{'eval_1':'/path/to/eval_1.jsonl'}`            |
+| `--eval-dataset` | JSON of task\:eval\_dataset\_path pairs | `{"eval_1":"/path/to/eval_1.jsonl"}`            |
 | `--project`      | Project name                            | `Project1`            |
 | `--num-episodes` | Number of training episodes             | `1`               |
 

applications/ColossalChat/rl_example.py

@@ -17,7 +17,7 @@
         default=None,
         help="Evaluation dataset for each task, please use json format to specify the dataset for each task. \
         For example: {'task1':'data_eval_task1.jsonl', 'task2':'data_eval_task2.jsonl'}, the jsonl file should be in the same format as the training dataset. \
-        The key is the task name, and the value is the path to the jsonl file",
+        The key is the task name, and the value is the path to the jsonl file, please replace sinple quotes with double quotes to conform to json format.",
     )
     parser.add_argument("-p", "--project", type=str, default="GRPO", help="Project name.")
     parser.add_argument("-e", "--num-episodes", type=int, default=1, help="Number of episodes to train.")