GPT2 custom & dataset metrics
This commit is contained in:
parent
bb87963601
commit
dc373e55a8
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
5359
projekt/GPT2_custom_sms_spam.ipynb
Normal file
5359
projekt/GPT2_custom_sms_spam.ipynb
Normal file
File diff suppressed because one or more lines are too long
File diff suppressed because it is too large
Load Diff
@ -62,6 +62,20 @@ Najważniejsze cechy:
|
|||||||
- Accuracy: 99%
|
- Accuracy: 99%
|
||||||
- MCC: 0.960
|
- MCC: 0.960
|
||||||
|
|
||||||
|
### Transformer Decoder - GPT2 - modyfikacja
|
||||||
|
Najważniejsze cechy:
|
||||||
|
- wytrenowany model gpt2
|
||||||
|
- typ modelu zmodyfikowany transformers.GPT2ForSequenceClassification - dodatkowe dwie warstwy liniowe
|
||||||
|
- input modelu - treść smsa
|
||||||
|
- output modelu - klasa 1 lub 2
|
||||||
|
- finetuning na zbiorze treningowym
|
||||||
|
- adamW optimizer
|
||||||
|
- learning rate 2e-5
|
||||||
|
- 8 batch size
|
||||||
|
- 4 epoch
|
||||||
|
- Accuracy: 99.1%
|
||||||
|
- MCC: 0.958
|
||||||
|
|
||||||
### Transformer Encoder-Decoder - T5
|
### Transformer Encoder-Decoder - T5
|
||||||
Najważniejsze cechy:
|
Najważniejsze cechy:
|
||||||
- wytrenowany model t5-base
|
- wytrenowany model t5-base
|
||||||
|
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue
Block a user