Hello All, wanted to how can we save the fine tuned model for future reference.
For example, I ran below code,
training_args = TrainingArguments(
output_dir=output_dir,
learning_rate=1e-5,
num_train_epochs=1,
weight_decay=0.01,
logging_steps=1,
max_steps=1
)
trainer = Trainer(
model=original_model,
args=training_args,
train_dataset=tokenized_datasets[‘train’],
eval_dataset=tokenized_datasets[‘validation’]
)
instruct_model = trainer.train()
Then, how can I save the instruct_model?