| Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:rte-2020-06-29-12:22/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: roberta-base | |
| Tokenizing training data. (len: 2490) | |
| Tokenizing eval data (len: 277) | |
| Loaded data and tokenized in 18.287664651870728s | |
| Training model across 1 GPUs | |
| ***** Running training ***** | |
| Num examples = 2490 | |
| Batch size = 16 | |
| Max sequence length = 128 | |
| Num steps = 775 | |
| Num epochs = 5 | |
| Learning rate = 2e-05 | |
| Eval accuracy: 59.92779783393502% | |
| Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:rte-2020-06-29-12:22/. | |
| Eval accuracy: 71.48014440433214% | |
| Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:rte-2020-06-29-12:22/. | |
| Eval accuracy: 75.45126353790613% | |
| Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:rte-2020-06-29-12:22/. | |
| Eval accuracy: 79.42238267148014% | |
| Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:rte-2020-06-29-12:22/. | |
| Eval accuracy: 78.33935018050542% | |
| Saved tokenizer <textattack.models.tokenizers.auto_tokenizer.AutoTokenizer object at 0x7f386dbd2e80> to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:rte-2020-06-29-12:22/. | |
| Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:rte-2020-06-29-12:22/README.md. | |
| Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:rte-2020-06-29-12:22/train_args.json. | |