From 9aca563489c76d2abb6d2ba1919de5641001e92c Mon Sep 17 00:00:00 2001
From: KINNNNNNG <137853302@qq.com>
Date: Tue, 6 Jun 2023 15:37:05 +0800
Subject: [PATCH] Update config.py

When I was training with ```chat/train.py```, I reported the following error after training:
```
Traceback (most recent call last):
  File "train.py", line 345, in <module>
    main()
  File "train.py", line 313, in main
    if data_args.dataset_config_name is not None:
AttributeError: 'DataArguments' object has no attribute 'dataset_config_name'
WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2461 closing signal SIGTERM
WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2462 closing signal SIGTERM
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 2460) of binary: /usr/bin/python
Traceback (most recent call last):
  File "/usr/local/bin/torchrun", line 8, in <module>
    sys.exit(main())
  File "/usr/local/lib/python3.7/dist-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 346, in wrapper
    return f(*args, **kwargs)
  File "/usr/local/lib/python3.7/dist-packages/torch/distributed/run.py", line 762, in main
    run(args)
  File "/usr/local/lib/python3.7/dist-packages/torch/distributed/run.py", line 756, in run
    )(*cmd_args)
  File "/usr/local/lib/python3.7/dist-packages/torch/distributed/launcher/api.py", line 132, in __call__
    return launch_agent(self._config, self._entrypoint, list(args))
  File "/usr/local/lib/python3.7/dist-packages/torch/distributed/launcher/api.py", line 248, in launch_agent
    failures=result.failures,
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
============================================================
train.py FAILED
------------------------------------------------------------
Failures:
  <NO_OTHER_FAILURES>
------------------------------------------------------------
Root Cause (first observed failure):
[0]:
  time      : 2023-06-06_07:00:57
  host      : ee11o7smse510-0
  rank      : 0 (local_rank: 0)
  exitcode  : 1 (pid: 2460)
  error_file: <N/A>
  traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
```

I looked at the ```config.py``` file and found that ```DataArguments``` was missing the ```dataset_config_name``` statement, I wrote a ```test.py``` for testing, After I added ```dataset_config_name```, the test passed.
```
import logging
import math
import os
import random
import sys
from itertools import chain

import datasets
import torch
import transformers
from config import DataArguments, ModelArguments, TrainingArguments
from datasets import load_dataset
from dialogues import get_dialogue_template, mask_user_labels, prepare_dialogue
from transformers import (AutoModelForCausalLM, AutoTokenizer, Trainer,
                          default_data_collator, set_seed)
from transformers.testing_utils import CaptureLogger
from transformers.trainer_utils import get_last_checkpoint
from utils import StarChatArgumentParser, hf_login

if __name__ == '__main__':

    parser = StarChatArgumentParser((ModelArguments, DataArguments, TrainingArguments))
    if len(sys.argv) == 2 and sys.argv[1].endswith(".yaml"):
        # If we pass only one argument to the script and it's the path to a YAML file,
        # let's parse it to get our arguments.
        model_args, data_args, training_args = parser.parse_yaml_file(os.path.abspath(sys.argv[1]))
    # parse command line args and yaml file
    elif len(sys.argv) > 2 and sys.argv[1].endswith(".yaml"):
        model_args, data_args, training_args = parser.parse_yaml_and_args(os.path.abspath(sys.argv[1]), sys.argv[2:])
    # parse command line args only
    else:
        model_args, data_args, training_args = parser.parse_args_into_dataclasses()

    kwargs = {}
    if data_args.dataset_name is not None:
        kwargs["dataset_tags"] = data_args.dataset_name
        if data_args.dataset_config_name is not None:
            kwargs["dataset_args"] = data_args.dataset_config_name
            kwargs["dataset"] = f"{data_args.dataset_name} {data_args.dataset_config_name}"
        else:
            kwargs["dataset"] = data_args.dataset_name
            kwargs["dataset_args"] = "default"


    print(data_args.dataset_config_name is not None)
    print(kwargs)
```
---
 chat/config.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/chat/config.py b/chat/config.py
index fcdc569..390d2ac 100644
--- a/chat/config.py
+++ b/chat/config.py
@@ -106,6 +106,9 @@ class DataArguments:
             "help": "The name of the dialogue template to use for conditioning the model. See h4.training.dialogues for choices."
         },
     )
+    dataset_config_name: Optional[str] = field(
+        default=None
+    )
 
 
 @dataclass