Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-imdb-2020-06-29-16:55/log.txt.
Loading nlp dataset imdb, split train.
Loading nlp dataset imdb, split test.
Loaded dataset. Found: 2 labels: ([0, 1])
Loading transformers AutoModelForSequenceClassification: albert-base-v2
Tokenizing training data. (len: 25000)
Tokenizing eval data (len: 25000)
Loaded data and tokenized in 121.69637775421143s
Training model across 4 GPUs
***** Running training *****
	Num examples = 25000
	Batch size = 32
	Max sequence length = 128
	Num steps = 3905
	Num epochs = 5
	Learning rate = 2e-05
Eval accuracy: 86.512%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-imdb-2020-06-29-16:55/.
Eval accuracy: 88.024%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-imdb-2020-06-29-16:55/.
Eval accuracy: 89.19200000000001%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-imdb-2020-06-29-16:55/.
Eval accuracy: 89.236%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-imdb-2020-06-29-16:55/.
Eval accuracy: 88.956%
Saved tokenizer <textattack.models.tokenizers.auto_tokenizer.AutoTokenizer object at 0x7f23881f8400> to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-imdb-2020-06-29-16:55/.
Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-imdb-2020-06-29-16:55/README.md.
Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-imdb-2020-06-29-16:55/train_args.json.