# model/tokenizer
model_name: "nomic-ai/gpt4all-gptj-multinode-deepspeed-finetuned-epoch_0"
tokenizer_name: "EleutherAI/gpt-j-6B"

# dataset
streaming: false
num_proc: 64
dataset_path: "data_multiplus" 
max_length: 1024
batch_size: 32 

# logging
seed: 42