Modelpublic
textattack/bert-base-uncased-MRPC

sourceHugging Faceupdated 5y agoView on Hugging Face
3likes32kdownloads
log.txt27 linesDownload Raw Back to root
1Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-glue:mrpc-2020-06-29-12:04/log.txt.2Loading [94mnlp[0m dataset [94mglue[0m, subset [94mmrpc[0m, split [94mtrain[0m.3Loading [94mnlp[0m dataset [94mglue[0m, subset [94mmrpc[0m, split [94mvalidation[0m.4Loaded dataset. Found: 2 labels: ([0, 1])5Loading transformers AutoModelForSequenceClassification: bert-base-uncased6Tokenizing training data. (len: 3668)7Tokenizing eval data (len: 408)8Loaded data and tokenized in 12.476295709609985s9Training model across 4 GPUs10***** Running training *****11	Num examples = 366812	Batch size = 1613	Max sequence length = 25614	Num steps = 114515	Num epochs = 516	Learning rate = 2e-0517Eval accuracy: 84.31372549019608%18Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-glue:mrpc-2020-06-29-12:04/.19Eval accuracy: 87.74509803921569%20Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-glue:mrpc-2020-06-29-12:04/.21Eval accuracy: 86.02941176470588%22Eval accuracy: 85.7843137254902%23Eval accuracy: 85.04901960784314%24Saved tokenizer <textattack.models.tokenizers.auto_tokenizer.AutoTokenizer object at 0x7f3a1d1a5d00> to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-glue:mrpc-2020-06-29-12:04/.25Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-glue:mrpc-2020-06-29-12:04/README.md.26Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-glue:mrpc-2020-06-29-12:04/train_args.json.27