output_dir="./finetuning-results",
overwrite_output_dir=True,
push_to_hub=True,
push_to_hub_model_id=base_model.split("/")[-1] + "-" + datetime.datetime.now().strftime("%Y-%m-%d-%H-%M"),
push_to_hub_organization="CLASS-MATE",
push_to_hub_token="TOKEN",
num_train_epochs=1,
per_device_train_batch_size=8,
gradient_accumulation_steps=1,
optim="paged_adamw_32bit",
# save_steps=500,
save_strategy="epoch",
logging_steps=50,
evaluation_strategy="steps",
eval_steps=500,
learning_rate=0.1,
weight_decay=0.001,
fp16=False,
bf16=False,
max_grad_norm=0.3,
# max_steps=-1,
warmup_ratio=0.03,
group_by_length=True,
lr_scheduler_type="constant",