log.txt

Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/distilbert-base-uncased-rotten_tomatoes-2020-06-24-12:26/log.txt.
Loading nlp dataset rotten_tomatoes, split train.
Loading nlp dataset rotten_tomatoes, split validation.
Filtering samples with labels outside of [0, 1, 2].
Filtered 8530 train samples to 8530 points.
Filtered 1066 dev samples to 1066 points.
Loaded dataset. Found: 2 labels: ([0, 1])
Loading transformers AutoModelForSequenceClassification: distilbert-base-uncased
Tokenizing training data. (len: 8530)
Tokenizing eval data (len: 1066)
Loaded data and tokenized in 6.951146125793457s
Training model across 4 GPUs
***** Running training *****
	Num examples = 8530
	Batch size = 128
	Max sequence length = 128
	Num steps = 198
	Num epochs = 3
	Learning rate = 1e-05
Eval accuracy: 81.61350844277673%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/distilbert-base-uncased-rotten_tomatoes-2020-06-24-12:26/.
Eval accuracy: 82.6454033771107%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/distilbert-base-uncased-rotten_tomatoes-2020-06-24-12:26/.
Eval accuracy: 83.95872420262664%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/distilbert-base-uncased-rotten_tomatoes-2020-06-24-12:26/.
Saved tokenizer <textattack.models.tokenizers.auto_tokenizer.AutoTokenizer object at 0x7f798097fac0> to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/distilbert-base-uncased-rotten_tomatoes-2020-06-24-12:26/.
Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/distilbert-base-uncased-rotten_tomatoes-2020-06-24-12:26/README.md.
Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/distilbert-base-uncased-rotten_tomatoes-2020-06-24-12:26/train_args.json.