SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

fix run_lm_modeling example command line

Browse Source
This commit is contained in:
thomwolf
2019-02-06 00:07:08 +01:00
parent 6179f537a3
commit ba37ddc5ce
1 changed files with 9 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
README.md
View File

@@ -680,14 +680,15 @@ Training one epoch on this corpus takes about 1:20h on 4 x NVIDIA Tesla P100 wit
```shell ```shell
python run_lm_finetuning.py \ python run_lm_finetuning.py \
--bert_model bert-base-cased --bert_model bert-base-uncased \
--do_train --do_lower_case \
--train_file samples/sample_text.txt --do_train \
--output_dir models --train_file ../samples/sample_text.txt \
--num_train_epochs 5.0 --output_dir models \
--learning_rate 3e-5 --num_train_epochs 5.0 \
--train_batch_size 32 --learning_rate 3e-5 \
--max_seq_length 128 --train_batch_size 32 \
--max_seq_length 128 \
``` ```
## Fine-tuning BERT-large on GPUs ## Fine-tuning BERT-large on GPUs