Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-rotten_tomatoes-2020-06-28-14:54/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: albert-base-v2
Tokenizing training data. (len: 8530)
Tokenizing eval data (len: 1066)
Loaded data and tokenized in 16.212775945663452s
Training model across 4 GPUs
***** Running training *****
	Num examples = 8530
	Batch size = 64
	Max sequence length = 128
	Num steps = 665
	Num epochs = 5
	Learning rate = 2e-05
Eval accuracy: 85.92870544090057%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-rotten_tomatoes-2020-06-28-14:54/.
Eval accuracy: 88.08630393996248%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-rotten_tomatoes-2020-06-28-14:54/.
Eval accuracy: 86.67917448405254%
Eval accuracy: 86.39774859287056%
Eval accuracy: 86.21013133208255%
Saved tokenizer <textattack.models.tokenizers.auto_tokenizer.AutoTokenizer object at 0x7f19d4bf0880> to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-rotten_tomatoes-2020-06-28-14:54/.
Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-rotten_tomatoes-2020-06-28-14:54/README.md.
Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-rotten_tomatoes-2020-06-28-14:54/train_args.json.