Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-rotten_tomatoes-2020-06-25-01:28/log.txt. Loading nlp dataset rotten_tomatoes, split train. Loading nlp dataset rotten_tomatoes, split validation. Loaded dataset. Found: 2 labels: ([0, 1]) Loading transformers AutoModelForSequenceClassification: bert-base-uncased Tokenizing training data. (len: 8530) Tokenizing eval data (len: 1066) Loaded data and tokenized in 8.81861162185669s Training model across 4 GPUs ***** Running training ***** Num examples = 8530 Batch size = 16 Max sequence length = 128 Num steps = 5330 Num epochs = 10 Learning rate = 2e-05 Eval accuracy: 85.27204502814259% Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-rotten_tomatoes-2020-06-25-01:28/. Eval accuracy: 85.74108818011257% Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-rotten_tomatoes-2020-06-25-01:28/. Eval accuracy: 85.45966228893059% Eval accuracy: 85.27204502814259% Eval accuracy: 87.5234521575985% Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-rotten_tomatoes-2020-06-25-01:28/. Eval accuracy: 85.92870544090057% Eval accuracy: 86.21013133208255% Eval accuracy: 86.11632270168855% Eval accuracy: 86.96060037523452% Eval accuracy: 86.86679174484053% Saved tokenizer to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-rotten_tomatoes-2020-06-25-01:28/. Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-rotten_tomatoes-2020-06-25-01:28/README.md. Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-rotten_tomatoes-2020-06-25-01:28/train_args.json.