Skip to content
Snippets Groups Projects
Commit dafc5c2f authored by jbreton's avatar jbreton
Browse files

Update Mistral hyper parameters and results

parent c1653711
No related branches found
No related tags found
No related merge requests found
......@@ -57,7 +57,8 @@ def fine_tune(base_model, new_model):
# Hyperparameters should beadjusted based on the hardware you using
training_arguments = TrainingArguments(
per_device_train_batch_size=2,
gradient_accumulation_steps=1,
gradient_accumulation_steps=2,
num_train_epochs=6,
learning_rate=1e-4,
logging_steps=2,
optim="adamw_torch",
......
Source diff could not be displayed: it is too large. Options to address this: view the blob.
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment