Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/distilbert-base-uncased-imdb-2020-06-30-09:57/log.txt. Loading nlp dataset imdb, split train. Loading nlp dataset imdb, split test. Loaded dataset. Found: 2 labels: ([0, 1]) Loading transformers AutoModelForSequenceClassification: distilbert-base-uncased Tokenizing training data. (len: 25000) Tokenizing eval data (len: 25000) Loaded data and tokenized in 76.20483636856079s Training model across 4 GPUs ***** Running training ***** Num examples = 25000 Batch size = 16 Max sequence length = 128 Num steps = 7810 Num epochs = 5 Learning rate = 2e-05 Eval accuracy: 87.312% Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/distilbert-base-uncased-imdb-2020-06-30-09:57/. Eval accuracy: 87.336% Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/distilbert-base-uncased-imdb-2020-06-30-09:57/. Eval accuracy: 88.0% Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/distilbert-base-uncased-imdb-2020-06-30-09:57/. Eval accuracy: 87.832% Eval accuracy: 87.736% Saved tokenizer to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/distilbert-base-uncased-imdb-2020-06-30-09:57/. Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/distilbert-base-uncased-imdb-2020-06-30-09:57/README.md. Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/distilbert-base-uncased-imdb-2020-06-30-09:57/train_args.json.