franziska/MasterarbeitCode
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

added to READMEs

Browse Source
This commit is contained in:
Franziska Marquis
2021-04-15 20:31:40 +02:00
parent 1ea0677029
commit 98c88fdfff
2 changed files with 8 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
final_Versions/README.md
View File

@@ -3,6 +3,8 @@ Unzip German FoodBERT models here!
They can be found under https://cloud.marquis.site/s/ZUVIIIQv6yznBj6 They can be found under https://cloud.marquis.site/s/ZUVIIIQv6yznBj6
For each version, the actual model is located in "output". "eval" contains the generated substitute recommendations for each version.
## Datasets ## Datasets
Each model has a folder "dataset" with the following files: Each model has a folder "dataset" with the following files:

6
train_model/README.md
View File

@@ -7,6 +7,12 @@ To create vocab.txt file, run **make_new_vocab.py**
# train German FoodBERT # train German FoodBERT
**language_modeling** **language_modeling**
This was executed on Google Colab with the following parameters:
!python /content/drive/MyDrive/masterarbeit/language_modeling.py --output_dir="/content/drive/MyDrive/masterarbeit/output" --model_type=bert --model_name=bert-base-german-cased --do_train --train_data_file="/content/drive/MyDrive/masterarbeit/data/training_data.txt" --do_eval --eval_data_file="/content/drive/MyDrive/masterarbeit/data/testing_data.txt" --mlm --line_by_line --per_device_train_batch_size=8 --gradient_accumulation_steps=2 --per_device_eval_batch_size=8 --save_total_limit=5 --save_steps=10000 --logging_steps=10000 --evaluation_strategy=epoch --model_name_or_path="bert-base-german-cased"
The exclamation mark at the beginning of the line is only needed on Google Colab and can be omitted when executing locally. Paths need to be adjusted when executing.
# Vocab Files: # Vocab Files:
**bert-base-german-cased_tokenizer.json**: original bert-base-german-cased tokenizer file **bert-base-german-cased_tokenizer.json**: original bert-base-german-cased tokenizer file