Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-rotten_tomatoes-2020-06-24-22:35/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 8.259030103683472s Training model across 4 GPUs ***** Running training ***** Num examples = 8530 Batch size = 64 Max sequence length = 128 Num steps = 1330 Num epochs = 10 Learning rate = 5e-05 Eval accuracy: 82.92682926829268% Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-rotten_tomatoes-2020-06-24-22:35/. Eval accuracy: 85.45966228893059% Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-rotten_tomatoes-2020-06-24-22:35/. Eval accuracy: 86.49155722326454% Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-rotten_tomatoes-2020-06-24-22:35/. Eval accuracy: 85.64727954971858% Eval accuracy: 87.5234521575985% Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-rotten_tomatoes-2020-06-24-22:35/. Eval accuracy: 85.92870544090057% Eval accuracy: 87.5234521575985% Eval accuracy: 86.77298311444653% Eval accuracy: 86.77298311444653% Eval accuracy: 86.49155722326454% Saved tokenizer to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-rotten_tomatoes-2020-06-24-22:35/. Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-rotten_tomatoes-2020-06-24-22:35/README.md. Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-rotten_tomatoes-2020-06-24-22:35/train_args.json.