Hello, I’m fine tuning an NLP model and wanted to know how to change the examples that are displayed in the model card when pushing the model to the hub.
This are my training arguments:
from transformers import TrainingArguments
batch_size = 64
# Show the training loss with every epoch
logging_steps = len(downsampled_dataset["train"]) // batch_size
model_name = model_checkpoint.split("/")[-1]
training_args = TrainingArguments(
output_dir=f"{model_name}-finetuned-spanish-corpus",
overwrite_output_dir=True,
evaluation_strategy="epoch",
learning_rate=2e-5,
weight_decay=0.01,
per_device_train_batch_size=batch_size,
per_device_eval_batch_size=batch_size,
push_to_hub=True,
fp16=True, # boost in speed
logging_steps=logging_steps,
)