PavanNeerudu
commited on
Commit
•
e0622b1
1
Parent(s):
5b2e1f2
Update README.md
Browse files
README.md
CHANGED
@@ -39,7 +39,7 @@ T5 is an encoder-decoder model pre-trained on a multi-task mixture of unsupervis
|
|
39 |
### Tokenization
|
40 |
Since, T5 is a text-to-text model, the labels of the dataset are converted as follows:
|
41 |
For each example, a sentence as been formed as **"mnli premise: " + mnli_premise + "hypothesis: " + mnli_hypothesis** and fed to the tokenizer to get the **input_ids** and **attention_mask**.
|
42 |
-
For each label,
|
43 |
During training, these inputs_ids having **pad** token are replaced with -100 so that loss is not calculated for them. Then these input ids are given as labels, and above attention_mask of labels
|
44 |
is given as decoder attention mask.
|
45 |
|
|
|
39 |
### Tokenization
|
40 |
Since, T5 is a text-to-text model, the labels of the dataset are converted as follows:
|
41 |
For each example, a sentence as been formed as **"mnli premise: " + mnli_premise + "hypothesis: " + mnli_hypothesis** and fed to the tokenizer to get the **input_ids** and **attention_mask**.
|
42 |
+
For each label, target is choosen as **"entailment"** if label is 0, else it is **"neutral"** if label is 1, else it is **"contradiction"** and tokenized to get **input_ids** and **attention_mask** .
|
43 |
During training, these inputs_ids having **pad** token are replaced with -100 so that loss is not calculated for them. Then these input ids are given as labels, and above attention_mask of labels
|
44 |
is given as decoder attention mask.
|
45 |
|