Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-glue:mrpc-2020-06-29-15:23/log.txt.
Loading [94mnlp[0m dataset [94mglue[0m, subset [94mmrpc[0m, split [94mtrain[0m.
Loading [94mnlp[0m dataset [94mglue[0m, subset [94mmrpc[0m, split [94mvalidation[0m.
Loaded dataset. Found: 2 labels: ([0, 1])
Loading transformers AutoModelForSequenceClassification: xlnet-base-cased
Tokenizing training data. (len: 3668)
Tokenizing eval data (len: 408)
Loaded data and tokenized in 14.01921534538269s
Training model across 4 GPUs
***** Running training *****
	Num examples = 3668
	Batch size = 32
	Max sequence length = 256
	Num steps = 570
	Num epochs = 5
	Learning rate = 5e-05
Eval accuracy: 70.83333333333334%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-glue:mrpc-2020-06-29-15:23/.
Eval accuracy: 77.94117647058823%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-glue:mrpc-2020-06-29-15:23/.
Eval accuracy: 88.97058823529412%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-glue:mrpc-2020-06-29-15:23/.
Eval accuracy: 83.57843137254902%
Eval accuracy: 86.51960784313727%
Saved tokenizer <textattack.models.tokenizers.auto_tokenizer.AutoTokenizer object at 0x7fa8a817ac10> to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-glue:mrpc-2020-06-29-15:23/.
Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-glue:mrpc-2020-06-29-15:23/README.md.
Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-glue:mrpc-2020-06-29-15:23/train_args.json.