Update log.txt
Browse files
log.txt
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-rotten_tomatoes-2020-06-28-14:54/log.txt.
|
| 2 |
+
Loading [94mnlp[0m dataset [94mrotten_tomatoes[0m, split [94mtrain[0m.
|
| 3 |
+
Loading [94mnlp[0m dataset [94mrotten_tomatoes[0m, split [94mvalidation[0m.
|
| 4 |
+
Loaded dataset. Found: 2 labels: ([0, 1])
|
| 5 |
+
Loading transformers AutoModelForSequenceClassification: albert-base-v2
|
| 6 |
+
Tokenizing training data. (len: 8530)
|
| 7 |
+
Tokenizing eval data (len: 1066)
|
| 8 |
+
Loaded data and tokenized in 16.212775945663452s
|
| 9 |
+
Training model across 4 GPUs
|
| 10 |
+
***** Running training *****
|
| 11 |
+
Num examples = 8530
|
| 12 |
+
Batch size = 64
|
| 13 |
+
Max sequence length = 128
|
| 14 |
+
Num steps = 665
|
| 15 |
+
Num epochs = 5
|
| 16 |
+
Learning rate = 2e-05
|
| 17 |
+
Eval accuracy: 85.92870544090057%
|
| 18 |
+
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-rotten_tomatoes-2020-06-28-14:54/.
|
| 19 |
+
Eval accuracy: 88.08630393996248%
|
| 20 |
+
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-rotten_tomatoes-2020-06-28-14:54/.
|
| 21 |
+
Eval accuracy: 86.67917448405254%
|
| 22 |
+
Eval accuracy: 86.39774859287056%
|
| 23 |
+
Eval accuracy: 86.21013133208255%
|
| 24 |
+
Saved tokenizer <textattack.models.tokenizers.auto_tokenizer.AutoTokenizer object at 0x7f19d4bf0880> to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-rotten_tomatoes-2020-06-28-14:54/.
|
| 25 |
+
Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-rotten_tomatoes-2020-06-28-14:54/README.md.
|
| 26 |
+
Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/albert-base-v2-rotten_tomatoes-2020-06-28-14:54/train_args.json.
|