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 d9924cc commit f6f8202Copy full SHA for f6f8202
examples/train/embedding/train_emb.sh
@@ -5,7 +5,10 @@ nproc_per_node=2
5
# --use_chat_template must be false to use generation template
6
# --dataloader_drop_last must be true or eval gather will throw error
7
# --model iic/gte-modernbert-base iic/gte_Qwen2-7B-instruct also supported
8
+# INFONCE_TEMPERATURE default value is 0.01, here we use 0.1 because it makes
9
+# the `sentence-transformers/stsb:positive` dataset result to a zero loss
10
CUDA_VISIBLE_DEVICES=0,1 \
11
+INFONCE_TEMPERATURE=0.1 \
12
NPROC_PER_NODE=$nproc_per_node \
13
swift sft \
14
--model Qwen/Qwen3-Embedding-0.6B \
0 commit comments