Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-yelp_polarity-2020-06-30-16:01/log.txt.
Loading nlp dataset yelp_polarity, split train.
Loading nlp dataset yelp_polarity, split test.
Loaded dataset. Found: 2 labels: ([0, 1])
Loading transformers AutoModelForSequenceClassification: bert-base-uncased
Tokenizing training data. (len: 560000)
Tokenizing eval data (len: 38000)
Loaded data and tokenized in 1064.7807202339172s
Training model across 1 GPUs
***** Running training *****
	Num examples = 560000
	Batch size = 8
	Max sequence length = 512
	Num steps = 350000
	Num epochs = 5
	Learning rate = 5e-05
Eval accuracy: 50.0%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-yelp_polarity-2020-06-30-16:01/.
Eval accuracy: 50.00526315789474%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-yelp_polarity-2020-06-30-16:01/.
Eval accuracy: 50.0%
Eval accuracy: 50.0%
Eval accuracy: 50.0%
Saved tokenizer <textattack.models.tokenizers.auto_tokenizer.AutoTokenizer object at 0x7f6bcb56cd00> to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-yelp_polarity-2020-06-30-16:01/.
Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-yelp_polarity-2020-06-30-16:01/README.md.
Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-yelp_polarity-2020-06-30-16:01/train_args.json.