Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-rotten_tomatoes-2020-06-28-16:10/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: xlnet-base-cased
Tokenizing training data. (len: 8530)
Tokenizing eval data (len: 1066)
Loaded data and tokenized in 25.242671012878418s
Training model across 1 GPUs
***** Running training *****
	Num examples = 8530
	Batch size = 8
	Max sequence length = 128
	Num steps = 5330
	Num epochs = 5
	Learning rate = 2e-05
Eval accuracy: 89.58724202626641%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-rotten_tomatoes-2020-06-28-16:10/.
Eval accuracy: 89.58724202626641%
Eval accuracy: 90.33771106941839%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-rotten_tomatoes-2020-06-28-16:10/.
Eval accuracy: 89.8686679174484%
Eval accuracy: 89.30581613508443%
Saved tokenizer <textattack.models.tokenizers.auto_tokenizer.AutoTokenizer object at 0x7fe1c08b56d0> to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-rotten_tomatoes-2020-06-28-16:10/.
Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-rotten_tomatoes-2020-06-28-16:10/README.md.
Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-rotten_tomatoes-2020-06-28-16:10/train_args.json.