riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 02:02:21 +06:00
Code Issues Actions 33 Packages Projects Releases Wiki Activity

Patched a few outdated parameters

Browse Source
This commit is contained in:
LysandreJik 2019-09-06 17:48:06 -04:00
parent f47f9a5874
commit 3f91338be9
1 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
examples/README.md
View File

@ -133,7 +133,7 @@ python run_glue.py \
--do_lower_case \
--data_dir $GLUE_DIR/$TASK_NAME \
--max_seq_length 128 \
--train_batch_size 32 \
--per_gpu_train_batch_size 32 \
--learning_rate 2e-5 \
--num_train_epochs 3.0 \
--output_dir /tmp/$TASK_NAME/
@ -174,7 +174,7 @@ python run_glue.py \
--do_lower_case \
--data_dir $GLUE_DIR/MRPC/ \
--max_seq_length 128 \
--train_batch_size 32 \
--per_gpu_train_batch_size 32 \
--learning_rate 2e-5 \
--num_train_epochs 3.0 \
--output_dir /tmp/mrpc_output/
@ -201,7 +201,7 @@ python run_glue.py \
--do_lower_case \
--data_dir $GLUE_DIR/MRPC/ \
--max_seq_length 128 \
--train_batch_size 32 \
--per_gpu_train_batch_size 32 \
--learning_rate 2e-5 \
--num_train_epochs 3.0 \
--output_dir /tmp/mrpc_output/ \
@ -226,7 +226,7 @@ python -m torch.distributed.launch \
--do_lower_case \
--data_dir $GLUE_DIR/MRPC/ \
--max_seq_length 128 \
--train_batch_size 8 \
--per_gpu_train_batch_size 8 \
--learning_rate 2e-5 \
--num_train_epochs 3.0 \
--output_dir /tmp/mrpc_output/
@ -260,7 +260,7 @@ python -m torch.distributed.launch \
--do_lower_case \
--data_dir $GLUE_DIR/MNLI/ \
--max_seq_length 128 \
--train_batch_size 8 \
--per_gpu_train_batch_size 8 \
--learning_rate 2e-5 \
--num_train_epochs 3.0 \
--output_dir output_dir \
@ -303,11 +303,11 @@ python run_squad.py \
--model_type bert \
--model_name_or_path bert-base-cased \
--do_train \
--do_predict \
--do_eval \
--do_lower_case \
--train_file $SQUAD_DIR/train-v1.1.json \
--predict_file $SQUAD_DIR/dev-v1.1.json \
--train_batch_size 12 \
--per_gpu_train_batch_size 12 \
--learning_rate 3e-5 \
--num_train_epochs 2.0 \
--max_seq_length 384 \
@ -332,7 +332,7 @@ python -m torch.distributed.launch --nproc_per_node=8 run_squad.py \
--model_type bert \
--model_name_or_path bert-base-cased \
--do_train \
--do_predict \
--do_eval \
--do_lower_case \
--train_file $SQUAD_DIR/train-v1.1.json \
--predict_file $SQUAD_DIR/dev-v1.1.json \
@ -341,7 +341,7 @@ python -m torch.distributed.launch --nproc_per_node=8 run_squad.py \
--max_seq_length 384 \
--doc_stride 128 \
--output_dir ../models/wwm_uncased_finetuned_squad/ \
--train_batch_size 24 \
--per_gpu_train_batch_size 24 \
--gradient_accumulation_steps 12
```