updated run files

run_multi_sup_example.sh

@@ -0,0 +1,36 @@
+#!/bin/bash
+
+# In this example, we show how to train SimCSE using multiple GPU cards and PyTorch's distributed data parallel on supervised NLI dataset.
+# Set how many GPUs to use
+
+NUM_GPU=4
+
+# Randomly set a port number
+# If you encounter "address already used" error, just run again or manually set an available port id.
+PORT_ID=$(expr $RANDOM + 1000)
+
+# Allow multiple threads
+export OMP_NUM_THREADS=8
+
+# Use distributed data parallel
+# If you only want to use one card, uncomment the following line and comment the line with "torch.distributed.launch"
+# python train.py \
+python -m torch.distributed.launch --nproc_per_node $NUM_GPU --master_port $PORT_ID train.py \
+    --model_name_or_path bert-base-uncased \
+    --train_file data/nli_for_simcse.csv \
+    --output_dir result/my-sup-simcse-bert-base-uncased \
+    --num_train_epochs 3 \
+    --per_device_train_batch_size 128 \
+    --learning_rate 5e-5 \
+    --max_seq_length 32 \
+    --evaluation_strategy steps \
+    --metric_for_best_model stsb_spearman \
+    --load_best_model_at_end \
+    --eval_steps 125 \
+    --pooler_type cls \
+    --overwrite_output_dir \
+    --temp 0.05 \
+    --do_train \
+    --do_eval \
+    --fp16 \
+    "$@"

run_sup_example.sh

@@ -1,24 +1,7 @@
-#!/bin/bash
-
-# In this example, we show how to train SimCSE using multiple GPU cards and PyTorch's distributed data parallel on supervised NLI dataset.
-# Set how many GPUs to use
-
-NUM_GPU=4
-
-# Randomly set a port number
-# If you encounter "address already used" error, just run again or manually set an available port id.
-PORT_ID=$(expr $RANDOM + 1000)
-
-# Allow multiple threads
-export OMP_NUM_THREADS=8
-
-# Use distributed data parallel
-# If you only want to use one card, uncomment the following line and comment the line with "torch.distributed.launch"
-# python train.py \
-python -m torch.distributed.launch --nproc_per_node $NUM_GPU --master_port $PORT_ID train.py \
-    --model_name_or_path bert-base-uncased \
-    --train_file data/nli_for_simcse.csv \
-    --output_dir result/my-sup-simcse-bert-base-uncased \
+python ../../SimCSE/train.py \
+    --model_name_or_path NbAiLab/nb-bert-base \
+    --train_file data/mnli_no_for_simcse.csv \
+    --output_dir result/sup-simcse-nb-bert-base \
     --num_train_epochs 3 \
     --per_device_train_batch_size 128 \
     --learning_rate 5e-5 \
@@ -32,5 +15,4 @@ python -m torch.distributed.launch --nproc_per_node $NUM_GPU --master_port $PORT
     --temp 0.05 \
     --do_train \
     --do_eval \
-    --fp16 \
     "$@"

run_unsup_example.sh

@@ -6,7 +6,7 @@
 
 python3 ../../SimCSE/train.py \
     --model_name_or_path NbAiLab/nb-bert-base \
-    --train_file data/wiki1m_for_simcse.txt \
+    --train_file data/nor_news_1998_2019_sentences_1M.txt \
     --output_dir result/unsup-simcse-nb-bert-bert-base \
     --num_train_epochs 1 \
     --per_device_train_batch_size 64 \