chtan
/

gpt4-alpaca-lora_mlp-30b

chtan commited on May 5, 2023

Commit

5bf3d06

1 Parent(s): 900082a

Fix the typo of batch size.

Files changed (1) hide show

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ torchrun --nproc_per_node=8 finetune.py \
     --data_path './alpaca_data_gpt4.json' \
     --output_dir './gpt4-alpaca-lora_mlp-30b' \
     --batch_size 128 \
-    --micro_batch_size 2 \
     --num_epochs 10 \
     --learning_rate 1e-4 \
     --cutoff_len 512 \

     --data_path './alpaca_data_gpt4.json' \
     --output_dir './gpt4-alpaca-lora_mlp-30b' \
     --batch_size 128 \
+    --micro_batch_size 8 \
     --num_epochs 10 \
     --learning_rate 1e-4 \
     --cutoff_len 512 \