We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 67a72a7 commit 180f6dbCopy full SHA for 180f6db
train.sh
@@ -55,7 +55,7 @@ deepspeed ${deepspeed_args} \
55
--dataset_path ${dataset_path} \
56
--output_dir ${output_dir} --overwrite_output_dir \
57
--num_train_epochs 1 \
58
- --learning_rate 1e-4 \
+ --learning_rate 1e-5 \
59
--block_size 1024 \
60
--per_device_train_batch_size 24 \
61
--use_dora 1 \
0 commit comments