Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-imdb-2020-06-30-02:43/log.txt.
Loading nlp dataset imdb, split train.
Loading nlp dataset imdb, split test.
Loaded dataset. Found: 2 labels: ([0, 1])
Loading transformers AutoModelForSequenceClassification: bert-base-uncased
Tokenizing training data. (len: 25000)
Tokenizing eval data (len: 25000)
Loaded data and tokenized in 77.80554986000061s
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: 88.884%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-imdb-2020-06-30-02:43/.
Eval accuracy: 88.92%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-imdb-2020-06-30-02:43/.
Eval accuracy: 88.716%
Eval accuracy: 88.79599999999999%
Eval accuracy: 89.088%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-imdb-2020-06-30-02:43/.
Saved tokenizer <textattack.models.tokenizers.auto_tokenizer.AutoTokenizer object at 0x7f17e4b2e940> to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-imdb-2020-06-30-02:43/.
Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-imdb-2020-06-30-02:43/README.md.
Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-imdb-2020-06-30-02:43/train_args.json.