system HF staff commited on
Commit
e923d3b
1 Parent(s): 0071cbb

Update log.txt

Browse files
Files changed (1) hide show
  1. log.txt +26 -0
log.txt ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:cola-2020-06-29-14:54/log.txt.
2
+ Loading nlp dataset glue, subset cola, split train.
3
+ Loading nlp dataset glue, subset cola, split validation.
4
+ Loaded dataset. Found: 2 labels: ([0, 1])
5
+ Loading transformers AutoModelForSequenceClassification: roberta-base
6
+ Tokenizing training data. (len: 8551)
7
+ Tokenizing eval data (len: 1043)
8
+ Loaded data and tokenized in 20.26492166519165s
9
+ Training model across 4 GPUs
10
+ ***** Running training *****
11
+ Num examples = 8551
12
+ Batch size = 32
13
+ Max sequence length = 128
14
+ Num steps = 1335
15
+ Num epochs = 5
16
+ Learning rate = 2e-05
17
+ Eval accuracy: 81.87919463087249%
18
+ Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:cola-2020-06-29-14:54/.
19
+ Eval accuracy: 85.0431447746884%
20
+ Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:cola-2020-06-29-14:54/.
21
+ Eval accuracy: 84.18024928092042%
22
+ Eval accuracy: 84.0843720038351%
23
+ Eval accuracy: 84.75551294343241%
24
+ Saved tokenizer <textattack.models.tokenizers.auto_tokenizer.AutoTokenizer object at 0x7f94dc097dc0> to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:cola-2020-06-29-14:54/.
25
+ Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:cola-2020-06-29-14:54/README.md.
26
+ Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:cola-2020-06-29-14:54/train_args.json.