From a6c4ee27fd1fb7c09c2bbb92705a4592e2b1ac7b Mon Sep 17 00:00:00 2001 From: Leandro von Werra Date: Tue, 31 Mar 2020 13:54:45 +0200 Subject: [PATCH] Add model cards (#3537) * feat: add model card bert-imdb * feat: add model card gpt2-imdb-pos * feat: add model card gpt2-imdb --- model_cards/lvwerra/bert-imdb/README.md | 14 +++++++++++ model_cards/lvwerra/gpt2-imdb-pos/README.md | 18 ++++++++++++++ model_cards/lvwerra/gpt2-imdb/README.md | 27 +++++++++++++++++++++ 3 files changed, 59 insertions(+) create mode 100644 model_cards/lvwerra/bert-imdb/README.md create mode 100644 model_cards/lvwerra/gpt2-imdb-pos/README.md create mode 100644 model_cards/lvwerra/gpt2-imdb/README.md diff --git a/model_cards/lvwerra/bert-imdb/README.md b/model_cards/lvwerra/bert-imdb/README.md new file mode 100644 index 0000000000..dcc9932979 --- /dev/null +++ b/model_cards/lvwerra/bert-imdb/README.md @@ -0,0 +1,14 @@ +# BERT-IMDB + +## What is it? +BERT (`bert-large-cased`) trained for sentiment classification on the [IMDB dataset](https://www.kaggle.com/lakshmi25npathi/imdb-dataset-of-50k-movie-reviews). + +## Training setting + +The model was trained on 80% of the IMDB dataset for sentiment classification for three epochs with a learning rate of `1e-5` with the `simpletransformers` library. The library uses a learning rate schedule. + +## Result +The model achieved 90% classification accuracy on the validation set. + +## Reference +The full experiment is available in the [tlr repo](https://lvwerra.github.io/trl/03-bert-imdb-training/). diff --git a/model_cards/lvwerra/gpt2-imdb-pos/README.md b/model_cards/lvwerra/gpt2-imdb-pos/README.md new file mode 100644 index 0000000000..f9d9e49425 --- /dev/null +++ b/model_cards/lvwerra/gpt2-imdb-pos/README.md @@ -0,0 +1,18 @@ +# GPT2-IMDB-pos + +## What is it? +A small GPT2 (`lvwerra/gpt2-imdb`) language model fine-tuned to produce positive movie reviews based the [IMDB dataset](https://www.kaggle.com/lakshmi25npathi/imdb-dataset-of-50k-movie-reviews). The model is trained with rewards from a BERT sentiment classifier (`lvwerra/gpt2-imdb`) via PPO. + +## Training setting +The model was trained for `100` optimisation steps with a batch size of `256` which corresponds to `25600` training samples. The full experiment setup can be found in the Jupyter notebook in the [trl repo](https://lvwerra.github.io/trl/04-gpt2-sentiment-ppo-training/). + +## Examples +A few examples of the model response to a query before and after optimisation: + +| query | response (before) | response (after) | rewards (before) | rewards (after) | +|-------|-------------------|------------------|------------------|-----------------| +|I'd never seen a |heavier, woodier example of Victorian archite... |film of this caliber, and I think it's wonder... |3.297736 |4.158653| +|I love John's work |but I actually have to write language as in w... |and I hereby recommend this film. I am really... |-1.904006 |4.159198 | +|I's a big struggle |to see anyone who acts in that way. by Jim Th... |, but overall I'm happy with the changes even ... |-1.595925 |2.651260| + + diff --git a/model_cards/lvwerra/gpt2-imdb/README.md b/model_cards/lvwerra/gpt2-imdb/README.md new file mode 100644 index 0000000000..6922a169e2 --- /dev/null +++ b/model_cards/lvwerra/gpt2-imdb/README.md @@ -0,0 +1,27 @@ +# GPT2-IMDB + +## What is it? +A GPT2 (`gpt2`) language model fine-tuned on the [IMDB dataset](https://www.kaggle.com/lakshmi25npathi/imdb-dataset-of-50k-movie-reviews). + +## Training setting + +The GPT2 language model was fine-tuned for 1 epoch on the IMDB dataset. All comments were joined into a single text file separated by the EOS token: + +``` +import pandas as pd +df = pd.read_csv("imdb-dataset.csv") +imdb_str = " <|endoftext|> ".join(df['review'].tolist()) + +with open ('imdb.txt', 'w') as f: + f.write(imdb_str) +``` + +To train the model the `run_language_modeling.py` script in the `transformer` library was used: + +``` +python run_language_modeling.py + --train_data_file imdb.txt + --output_dir gpt2-imdb + --model_type gpt2 + --model_name_or_path gpt2 +```