jarodrigues
commited on
Commit
•
5ae56f3
1
Parent(s):
7c17f88
Update README.md
Browse files
README.md
CHANGED
@@ -140,7 +140,8 @@ The model can be used by fine-tuning it for a specific task:
|
|
140 |
>>> dataset = load_dataset("PORTULAN/glueptpt", "rte")
|
141 |
|
142 |
>>> def tokenize_function(examples):
|
143 |
-
... return tokenizer(examples["
|
|
|
144 |
>>> tokenized_datasets = dataset.map(tokenize_function, batched=True)
|
145 |
|
146 |
>>> training_args = TrainingArguments(output_dir="albertina-pt-pt-rte", evaluation_strategy="epoch")
|
@@ -150,6 +151,7 @@ The model can be used by fine-tuning it for a specific task:
|
|
150 |
... train_dataset=tokenized_datasets["train"],
|
151 |
... eval_dataset=tokenized_datasets["validation"],
|
152 |
... )
|
|
|
153 |
>>> trainer.train()
|
154 |
|
155 |
```
|
|
|
140 |
>>> dataset = load_dataset("PORTULAN/glueptpt", "rte")
|
141 |
|
142 |
>>> def tokenize_function(examples):
|
143 |
+
... return tokenizer(examples["sentence1"], examples["sentence2"], padding="max_length", truncation=True)
|
144 |
+
|
145 |
>>> tokenized_datasets = dataset.map(tokenize_function, batched=True)
|
146 |
|
147 |
>>> training_args = TrainingArguments(output_dir="albertina-pt-pt-rte", evaluation_strategy="epoch")
|
|
|
151 |
... train_dataset=tokenized_datasets["train"],
|
152 |
... eval_dataset=tokenized_datasets["validation"],
|
153 |
... )
|
154 |
+
|
155 |
>>> trainer.train()
|
156 |
|
157 |
```
|