I wrote a code that will fine-tine my QnA model using huggingface. The code will import questions and answers from a json file and then fine tune a HF Question-Answer model with the data from the json file. However, things went awry from then onwards, when I get this traceback:
Traceback (most recent call last):
File "C:\Users\Philip Chen\OneDrive\Documents\ML\machineLearning.py", line 45, in <module>
trainer.train()
File "C:\Users\Philip Chen\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\trainer.py", line 1859, in train
return inner_training_loop(
File "C:\Users\Philip Chen\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\trainer.py", line 2165, in _inner_training_loop
for step, inputs in enumerate(epoch_iterator):
File "C:\Users\Philip Chen\AppData\Local\Programs\Python\Python310\lib\site-packages\accelerate\data_loader.py", line 454, in __iter__
current_batch = next(dataloader_iter)
File "C:\Users\Philip Chen\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\utils\data\dataloader.py", line 631, in __next__
data = self._next_data()
File "C:\Users\Philip Chen\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\utils\data\dataloader.py", line 675, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "C:\Users\Philip Chen\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\utils\data\_utils\fetch.py", line 51, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "C:\Users\Philip Chen\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\utils\data\_utils\fetch.py", line 51, in <listcomp>
data = [self.dataset[idx] for idx in possibly_batched_index]
File "C:\Users\Philip Chen\AppData\Local\Programs\Python\Python310\lib\site-packages\datasets\dataset_dict.py", line 81, in __getitem__
raise KeyError(
KeyError: "Invalid key: 0. Please first select a split. For example: `my_dataset_dictionary['train'][0]`. Available splits: ['train']"
from the offending line:
trainer.train()
And this is my entire code:
# https://www.mlexpert.io/blog/alpaca-fine-tuning
# https://wellsr.com/python/fine-tuning-huggingface-models-in-tensorflow-keras/
# https://learnopencv.com/fine-tuning-bert/
# https://medium.com/@karary/nlp-fine-tune-question-answering-model-%E5%AF%A6%E4%BD%9C-3-model-training-%E5%84%B2%E5%AD%98%E8%88%87-inference-13d2a5bf5c32
import transformers as tf
import datasets as ds
import pandas as pd
import numpy as np
import torch
import json
############## Check if CUDA is enabled. ################
hasCUDA=torch.cuda.is_available()
print(f"CUDA Enabled? {hasCUDA}")
device="cuda" if hasCUDA else "cpu"
############## Loading file and populating data ################
fileName="qna.json"
trainDS=ds.load_dataset("json", data_files=fileName)
evalDS=ds.load_dataset("json", data_files=fileName)
# rawDS=ds.load_dataset('squad')
############## Model ##########################################
modelName="./distilbert-base-cased" #or replace the model name with whatever you feel like.
config=tf.AutoConfig.from_pretrained(modelName+"/config.json")
model=tf.AutoModelForQuestionAnswering.from_pretrained(modelName,config=config)
tokenizer=tf.AutoTokenizer.from_pretrained(modelName)
############## Training #######################################
trnArgs=tf.TrainingArguments(
output_dir="./",
evaluation_strategy="epoch",
save_strategy="epoch",
learning_rate=2e-5,
num_train_epochs=3,
remove_unused_columns=False,
fp16=True
)
trainer=tf.Trainer(
model=model,
args=trnArgs,
train_dataset=trainDS,
eval_dataset=evalDS,
tokenizer=tokenizer
)
trainer.train()
This is the JSON file that contains the questions:
{"text": "Who wrote Charlie and the Chocolate Factory?", "label": "Roald Dahl"}
{"text": "Name a few ways to treat constipation naturally.", "label": "Exercise regularly, eat more fibers, and drink more water."}
{"text": "Where is the longest roller coaster located?", "label": "Nagashima, Japan. The name of the coaster is Steel Dragon 2000."}
{"text": "What are the 11 herbs and spices that Colonel Sanders used in KFC?", "label": "Nobody knows, as it's a secret."}
{"text": "Who wrote Les Miserables?", "label": "Victor Hugo"}
{"text": "What is the Watergate Scandal?", "label": "The Watergate scandal was a significant political controversy in the United States during the presidency of Richard Nixon from 1972 to 1974, ultimately resulting in Nixon's resignation. It originated from attempts by the Nixon administration to conceal its involvement in the June 17, 1972, break-in at the Democratic National Committee headquarters located in the Watergate Office Building in Washington, D.C."}
{"text": "What is Obama's most famous quote?", "label": "'Yes we can!'"}
Any suggestions on how I can fix this thing?
The issue lies in how you create the train
and test
datasets. Since your dataset is already split into JSON files, you need to specify the split
when reading the data using the split
parameter. If you don't specify the split every time you run ds.load_dataset
, it automatically creates train and test splits for you. According to the function documentation:
split (`Split` or `str`):
Which split of the data to load.
**If `None`, it will return a `dict` with all splits** (typically `datasets.Split.TRAIN` and `datasets.Split.TEST`).
If a split is provided, it will return a single Dataset.
Splits can be combined and specified like in tensorflow-datasets.
To address this issue, use the following code:
trainDS = ds.load_dataset("json", data_files=fileName, split='train')
evalDS = ds.load_dataset("json", data_files=fileName, split='test')