I am finetuning hugging face âHuggingFaceH4/starchat-alphaâ model for making a data science text to code generating bot.
This is the format of my dataset:
train: Dataset({
features: [âinput_idsâ, âlabelsâ],
num_rows: 5012
})
test: Dataset({
features: [âinput_idsâ, âlabelsâ],
num_rows: 1325
})
})
and the structure of the dataset looks somewhat like this, which was explained in starcoder documentation,
<|system|>
Below is a dialogue between a human and an ANUJ_AI
<|end|>
<|user|>
Minimum count of ind⌠so on
<|end|>
<|assistant|>
def possible ( x , S , N ) : âŚso on
<|end|>
I am loading the model on my colab in 8 bit format using transformer BitsAndBytesConfig for saving memory, then loaded the model using a device map which was made using transformers AutoConfig and the acclerate which divided my model amoung âgpuâ, âcpuâ RAM and my âdiskâ.
Once the model and its checkpoints were downloaded successfully then i used transformers.Trainer to train the model on my custom dataset.
my using the below code:
but i am always getting this error =:
Please help me out with this error, if anyone has prior experience in this.
Your inputs will be highly appreciated.
Thank You!