system HF staff commited on
Commit
d428871
1 Parent(s): 52622bf

Update log.txt

Browse files
Files changed (1) hide show
  1. log.txt +27 -0
log.txt ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-imdb-2020-06-30-02:43/log.txt.
2
+ Loading nlp dataset imdb, split train.
3
+ Loading nlp dataset imdb, split test.
4
+ Loaded dataset. Found: 2 labels: ([0, 1])
5
+ Loading transformers AutoModelForSequenceClassification: bert-base-uncased
6
+ Tokenizing training data. (len: 25000)
7
+ Tokenizing eval data (len: 25000)
8
+ Loaded data and tokenized in 77.80554986000061s
9
+ Training model across 4 GPUs
10
+ ***** Running training *****
11
+ Num examples = 25000
12
+ Batch size = 16
13
+ Max sequence length = 128
14
+ Num steps = 7810
15
+ Num epochs = 5
16
+ Learning rate = 2e-05
17
+ Eval accuracy: 88.884%
18
+ Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-imdb-2020-06-30-02:43/.
19
+ Eval accuracy: 88.92%
20
+ Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-imdb-2020-06-30-02:43/.
21
+ Eval accuracy: 88.716%
22
+ Eval accuracy: 88.79599999999999%
23
+ Eval accuracy: 89.088%
24
+ Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-imdb-2020-06-30-02:43/.
25
+ Saved tokenizer <textattack.models.tokenizers.auto_tokenizer.AutoTokenizer object at 0x7f17e4b2e940> to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-imdb-2020-06-30-02:43/.
26
+ Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-imdb-2020-06-30-02:43/README.md.
27
+ Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-imdb-2020-06-30-02:43/train_args.json.