Traceback (most recent call last):
File "finetune_chat.py", line 180, in
train_data = train_val["train"].shuffle().map(PROMPT.preprocess_train, num_proc=num_proc)
File "/home/vaeput/miniconda3/envs/llama/lib/python3.8/site-packages/datasets/arrow_dataset.py", line 563, in wrapper
out: Union["Dataset", "DatasetDict"] = func(self, *args, *kwargs)
File "/home/vaeput/miniconda3/envs/llama/lib/python3.8/site-packages/datasets/arrow_dataset.py", line 528, in wrapper
out: Union["Dataset", "DatasetDict"] = func(self, args, **kwargs)
File "/home/vaeput/miniconda3/envs/llama/lib/python3.8/site-packages/datasets/arrow_dataset.py", line 3046, in map
for rank, done, content in iflatmap_unordered(
File "/home/vaeput/miniconda3/envs/llama/lib/python3.8/site-packages/datasets/utils/py_utils.py", line 1373, in iflatmap_unordered
[async_result.get() for async_result in async_results]
File "/home/vaeput/miniconda3/envs/llama/lib/python3.8/site-packages/datasets/utils/py_utils.py", line 1373, in
[async_result.get() for async_result in async_results]
File "/home/vaeput/miniconda3/envs/llama/lib/python3.8/site-packages/multiprocess/pool.py", line 771, in get
raise self._value
IndexError: string index out of range
代码如下 python finetune_chat.py --data_path merge_sample.json --test_size 1 报错如下
Traceback (most recent call last): File "finetune_chat.py", line 180, in
train_data = train_val["train"].shuffle().map(PROMPT.preprocess_train, num_proc=num_proc)
File "/home/vaeput/miniconda3/envs/llama/lib/python3.8/site-packages/datasets/arrow_dataset.py", line 563, in wrapper
out: Union["Dataset", "DatasetDict"] = func(self, *args, *kwargs)
File "/home/vaeput/miniconda3/envs/llama/lib/python3.8/site-packages/datasets/arrow_dataset.py", line 528, in wrapper
out: Union["Dataset", "DatasetDict"] = func(self, args, **kwargs)
File "/home/vaeput/miniconda3/envs/llama/lib/python3.8/site-packages/datasets/arrow_dataset.py", line 3046, in map
for rank, done, content in iflatmap_unordered(
File "/home/vaeput/miniconda3/envs/llama/lib/python3.8/site-packages/datasets/utils/py_utils.py", line 1373, in iflatmap_unordered
[async_result.get() for async_result in async_results]
File "/home/vaeput/miniconda3/envs/llama/lib/python3.8/site-packages/datasets/utils/py_utils.py", line 1373, in
[async_result.get() for async_result in async_results]
File "/home/vaeput/miniconda3/envs/llama/lib/python3.8/site-packages/multiprocess/pool.py", line 771, in get
raise self._value
IndexError: string index out of range