system HF staff commited on
Commit
e928596
1 Parent(s): 6e2fa5e

Update log.txt

Browse files
Files changed (1) hide show
  1. log.txt +28 -0
log.txt ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:rte-2020-06-29-12:22/log.txt.
2
+ Loading nlp dataset glue, subset rte, split train.
3
+ Loading nlp dataset glue, subset rte, split validation.
4
+ Loaded dataset. Found: 2 labels: ([0, 1])
5
+ Loading transformers AutoModelForSequenceClassification: roberta-base
6
+ Tokenizing training data. (len: 2490)
7
+ Tokenizing eval data (len: 277)
8
+ Loaded data and tokenized in 18.287664651870728s
9
+ Training model across 1 GPUs
10
+ ***** Running training *****
11
+ Num examples = 2490
12
+ Batch size = 16
13
+ Max sequence length = 128
14
+ Num steps = 775
15
+ Num epochs = 5
16
+ Learning rate = 2e-05
17
+ Eval accuracy: 59.92779783393502%
18
+ Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:rte-2020-06-29-12:22/.
19
+ Eval accuracy: 71.48014440433214%
20
+ Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:rte-2020-06-29-12:22/.
21
+ Eval accuracy: 75.45126353790613%
22
+ Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:rte-2020-06-29-12:22/.
23
+ Eval accuracy: 79.42238267148014%
24
+ Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:rte-2020-06-29-12:22/.
25
+ Eval accuracy: 78.33935018050542%
26
+ Saved tokenizer <textattack.models.tokenizers.auto_tokenizer.AutoTokenizer object at 0x7f386dbd2e80> to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:rte-2020-06-29-12:22/.
27
+ Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:rte-2020-06-29-12:22/README.md.
28
+ Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/roberta-base-glue:rte-2020-06-29-12:22/train_args.json.