Skip to content

GitLab

Unverified Commit 3d5dea9b authored by Patrick von Platen's avatar Patrick von Platen Committed by GitHub
Browse files

Add example batch size to all commands (#15596)

parent cb7ed6e0
Show whitespace changes
Inline Side-by-side
Showing with 12 additions and 0 deletions
examples/pytorch/language-modeling/README.md
View file @ 3d5dea9b
...@@ -39,6 +39,8 @@ python run_clm.py \ ...@@ -39,6 +39,8 @@ python run_clm.py \
--model_name_or_path gpt2 \ --model_name_or_path gpt2 \
--dataset_name wikitext \ --dataset_name wikitext \
--dataset_config_name wikitext-2-raw-v1 \ --dataset_config_name wikitext-2-raw-v1 \
--per_device_train_batch_size 8 \
--per_device_eval_batch_size 8 \
--do_train \ --do_train \
--do_eval \ --do_eval \
--output_dir /tmp/test-clm --output_dir /tmp/test-clm
...@@ -54,6 +56,8 @@ python run_clm.py \ ...@@ -54,6 +56,8 @@ python run_clm.py \
--model_name_or_path gpt2 \ --model_name_or_path gpt2 \
--train_file path_to_train_file \ --train_file path_to_train_file \
--validation_file path_to_validation_file \ --validation_file path_to_validation_file \
--per_device_train_batch_size 8 \
--per_device_eval_batch_size 8 \
--do_train \ --do_train \
--do_eval \ --do_eval \
--output_dir /tmp/test-clm --output_dir /tmp/test-clm
...@@ -83,6 +87,8 @@ python run_mlm.py \ ...@@ -83,6 +87,8 @@ python run_mlm.py \
--model_name_or_path roberta-base \ --model_name_or_path roberta-base \
--dataset_name wikitext \ --dataset_name wikitext \
--dataset_config_name wikitext-2-raw-v1 \ --dataset_config_name wikitext-2-raw-v1 \
--per_device_train_batch_size 8 \
--per_device_eval_batch_size 8 \
--do_train \ --do_train \
--do_eval \ --do_eval \
--output_dir /tmp/test-mlm --output_dir /tmp/test-mlm
...@@ -95,6 +101,8 @@ python run_mlm.py \ ...@@ -95,6 +101,8 @@ python run_mlm.py \
--model_name_or_path roberta-base \ --model_name_or_path roberta-base \
--train_file path_to_train_file \ --train_file path_to_train_file \
--validation_file path_to_validation_file \ --validation_file path_to_validation_file \
--per_device_train_batch_size 8 \
--per_device_eval_batch_size 8 \
--do_train \ --do_train \
--do_eval \ --do_eval \
--output_dir /tmp/test-mlm --output_dir /tmp/test-mlm
...@@ -139,6 +147,8 @@ python run_plm.py \ ...@@ -139,6 +147,8 @@ python run_plm.py \
--model_name_or_path=xlnet-base-cased \ --model_name_or_path=xlnet-base-cased \
--dataset_name wikitext \ --dataset_name wikitext \
--dataset_config_name wikitext-2-raw-v1 \ --dataset_config_name wikitext-2-raw-v1 \
--per_device_train_batch_size 8 \
--per_device_eval_batch_size 8 \
--do_train \ --do_train \
--do_eval \ --do_eval \
--output_dir /tmp/test-plm --output_dir /tmp/test-plm
...@@ -151,6 +161,8 @@ python run_plm.py \ ...@@ -151,6 +161,8 @@ python run_plm.py \
--model_name_or_path=xlnet-base-cased \ --model_name_or_path=xlnet-base-cased \
--train_file path_to_train_file \ --train_file path_to_train_file \
--validation_file path_to_validation_file \ --validation_file path_to_validation_file \
--per_device_train_batch_size 8 \
--per_device_eval_batch_size 8 \
--do_train \ --do_train \
--do_eval \ --do_eval \
--output_dir /tmp/test-plm --output_dir /tmp/test-plm
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment