From 6ad8ba24ba42fcbe4bda5a0136fbb84b274fc126 Mon Sep 17 00:00:00 2001 From: Wojciech Jarmosz Date: Tue, 22 Jun 2021 00:28:06 +0200 Subject: [PATCH] Fix --- fine_tuning.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fine_tuning.py b/fine_tuning.py index 93dcfca..d873931 100644 --- a/fine_tuning.py +++ b/fine_tuning.py @@ -29,7 +29,7 @@ class CustomDataset(torch.utils.data.Dataset): return len(self.encodings["input_ids"]) data_train = list(zip(data_train_X, data_train_Y)) -data_train = random.sample(data_train, 180000) +data_train = random.sample(data_train, 50000) tokenizer = BertTokenizer.from_pretrained("bert-base-uncased") train_X = tokenizer([text[0] for text in data_train], truncation=True, padding=True)