# model/tokenizer
model_name: "nomic-ai/gpt4all-warmup-lr-epoch_1"
tokenizer_name: "EleutherAI/gpt-j-6B"

# dataset
streaming: false
num_proc: 64
dataset_path: "nomic-ai/turbo-500k-multi" 
max_length: 1024
batch_size: 32 

# logging
seed: 42