Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-rotten_tomatoes-2020-06-25-00:42/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 5.994918584823608s
Training model across 4 GPUs
***** Running training *****
	Num examples = 8530
	Batch size = 128
	Max sequence length = 128
	Num steps = 660
	Num epochs = 10
	Learning rate = 2e-05
Eval accuracy: 81.98874296435272%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-rotten_tomatoes-2020-06-25-00:42/.
Eval accuracy: 88.55534709193246%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-rotten_tomatoes-2020-06-25-00:42/.
Eval accuracy: 86.86679174484053%
Eval accuracy: 86.67917448405254%
Eval accuracy: 86.58536585365853%
Eval accuracy: 86.02251407129457%
Eval accuracy: 86.02251407129457%
Eval accuracy: 86.49155722326454%
Eval accuracy: 85.74108818011257%
Eval accuracy: 85.92870544090057%
Saved tokenizer <textattack.models.tokenizers.auto_tokenizer.AutoTokenizer object at 0x7fb7daaf89d0> to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-rotten_tomatoes-2020-06-25-00:42/.
Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-rotten_tomatoes-2020-06-25-00:42/README.md.
Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-rotten_tomatoes-2020-06-25-00:42/train_args.json.