Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-glue:qqp-2020-06-30-00:07/log.txt.
Loading [94mnlp[0m dataset [94mglue[0m, subset [94mqqp[0m, split [94mtrain[0m.
Loading [94mnlp[0m dataset [94mglue[0m, subset [94mqqp[0m, split [94mvalidation[0m.
Loaded dataset. Found: 2 labels: ([0, 1])
Loading transformers AutoModelForSequenceClassification: albert-base-v2
Tokenizing training data. (len: 363849)
Tokenizing eval data (len: 40430)
Loaded data and tokenized in 514.5082082748413s
Training model across 1 GPUs
***** Running training *****
	Num examples = 363849
	Batch size = 32
	Max sequence length = 128
	Num steps = 56850
	Num epochs = 5
	Learning rate = 5e-05
Eval accuracy: 87.80361117981697%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-glue:qqp-2020-06-30-00:07/.
Eval accuracy: 89.3915409349493%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-glue:qqp-2020-06-30-00:07/.
Eval accuracy: 90.29680930002473%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-glue:qqp-2020-06-30-00:07/.
Eval accuracy: 90.73707642839476%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-glue:qqp-2020-06-30-00:07/.
Eval accuracy: 90.4575810042048%
Saved tokenizer <textattack.models.tokenizers.auto_tokenizer.AutoTokenizer object at 0x7fa7b6287970> to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-glue:qqp-2020-06-30-00:07/.
Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-glue:qqp-2020-06-30-00:07/README.md.
Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-glue:qqp-2020-06-30-00:07/train_args.json.