Update log.txt
Browse files
log.txt
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-glue:rte-2020-06-29-14:24/log.txt.
|
| 2 |
+
Loading [94mnlp[0m dataset [94mglue[0m, subset [94mrte[0m, split [94mtrain[0m.
|
| 3 |
+
Loading [94mnlp[0m dataset [94mglue[0m, subset [94mrte[0m, split [94mvalidation[0m.
|
| 4 |
+
Loaded dataset. Found: 2 labels: ([0, 1])
|
| 5 |
+
Loading transformers AutoModelForSequenceClassification: bert-base-uncased
|
| 6 |
+
Tokenizing training data. (len: 2490)
|
| 7 |
+
Tokenizing eval data (len: 277)
|
| 8 |
+
Loaded data and tokenized in 14.295648097991943s
|
| 9 |
+
Training model across 1 GPUs
|
| 10 |
+
***** Running training *****
|
| 11 |
+
Num examples = 2490
|
| 12 |
+
Batch size = 128
|
| 13 |
+
Max sequence length = 128
|
| 14 |
+
Num steps = 95
|
| 15 |
+
Num epochs = 5
|
| 16 |
+
Learning rate = 3e-05
|
| 17 |
+
Failed to predict with model <class 'transformers.modeling_bert.BertForSequenceClassification'>. Check tokenizer configuration.
|
| 18 |
+
Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-glue:rte-2020-06-29-14:24/log.txt.
|
| 19 |
+
Loading [94mnlp[0m dataset [94mglue[0m, subset [94mrte[0m, split [94mtrain[0m.
|
| 20 |
+
Loading [94mnlp[0m dataset [94mglue[0m, subset [94mrte[0m, split [94mvalidation[0m.
|
| 21 |
+
Loaded dataset. Found: 2 labels: ([0, 1])
|
| 22 |
+
Loading transformers AutoModelForSequenceClassification: bert-base-uncased
|
| 23 |
+
Tokenizing training data. (len: 2490)
|
| 24 |
+
Tokenizing eval data (len: 277)
|
| 25 |
+
Loaded data and tokenized in 13.395596742630005s
|
| 26 |
+
Training model across 1 GPUs
|
| 27 |
+
***** Running training *****
|
| 28 |
+
Num examples = 2490
|
| 29 |
+
Batch size = 8
|
| 30 |
+
Max sequence length = 128
|
| 31 |
+
Num steps = 1555
|
| 32 |
+
Num epochs = 5
|
| 33 |
+
Learning rate = 2e-05
|
| 34 |
+
Eval accuracy: 68.23104693140795%
|
| 35 |
+
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/.
|
| 36 |
+
Eval accuracy: 70.03610108303249%
|
| 37 |
+
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/.
|
| 38 |
+
Eval accuracy: 72.56317689530685%
|
| 39 |
+
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/.
|
| 40 |
+
Eval accuracy: 69.67509025270758%
|
| 41 |
+
Eval accuracy: 69.31407942238266%
|
| 42 |
+
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/.
|
| 43 |
+
Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-glue:rte-2020-06-29-14:24/README.md.
|
| 44 |
+
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.
|