| Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-glue:rte-2020-06-29-14:24/log.txt. | |
| Loading [94mnlp[0m dataset [94mglue[0m, subset [94mrte[0m, split [94mtrain[0m. | |
| Loading [94mnlp[0m dataset [94mglue[0m, subset [94mrte[0m, split [94mvalidation[0m. | |
| Loaded dataset. Found: 2 labels: ([0, 1]) | |
| Loading transformers AutoModelForSequenceClassification: bert-base-uncased | |
| Tokenizing training data. (len: 2490) | |
| Tokenizing eval data (len: 277) | |
| Loaded data and tokenized in 14.295648097991943s | |
| Training model across 1 GPUs | |
| ***** Running training ***** | |
| Num examples = 2490 | |
| Batch size = 128 | |
| Max sequence length = 128 | |
| Num steps = 95 | |
| Num epochs = 5 | |
| Learning rate = 3e-05 | |
| Failed to predict with model <class 'transformers.modeling_bert.BertForSequenceClassification'>. Check tokenizer configuration. | |
| Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-glue:rte-2020-06-29-14:24/log.txt. | |
| Loading [94mnlp[0m dataset [94mglue[0m, subset [94mrte[0m, split [94mtrain[0m. | |
| Loading [94mnlp[0m dataset [94mglue[0m, subset [94mrte[0m, split [94mvalidation[0m. | |
| Loaded dataset. Found: 2 labels: ([0, 1]) | |
| Loading transformers AutoModelForSequenceClassification: bert-base-uncased | |
| Tokenizing training data. (len: 2490) | |
| Tokenizing eval data (len: 277) | |
| Loaded data and tokenized in 13.395596742630005s | |
| Training model across 1 GPUs | |
| ***** Running training ***** | |
| Num examples = 2490 | |
| Batch size = 8 | |
| Max sequence length = 128 | |
| Num steps = 1555 | |
| Num epochs = 5 | |
| Learning rate = 2e-05 | |
| Eval accuracy: 68.23104693140795% | |
| Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-glue:rte-2020-06-29-14:24/. | |
| Eval accuracy: 70.03610108303249% | |
| Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-glue:rte-2020-06-29-14:24/. | |
| Eval accuracy: 72.56317689530685% | |
| Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-glue:rte-2020-06-29-14:24/. | |
| Eval accuracy: 69.67509025270758% | |
| Eval accuracy: 69.31407942238266% | |
| Saved tokenizer <textattack.models.tokenizers.auto_tokenizer.AutoTokenizer object at 0x7fc688911c10> to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-glue:rte-2020-06-29-14:24/. | |
| Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-glue:rte-2020-06-29-14:24/README.md. | |
| Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-glue:rte-2020-06-29-14:24/train_args.json. | |