SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

[Follow up 213]

Browse Source 
Masked indices should have -1 and not -100. Updating documentation + scripts that were forgotten
This commit is contained in:
Lysandre
2020-02-03 16:08:05 -05:00
parent 522c5b5533
commit 239dd23f64
14 changed files with 37 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/contrib/run_openai_gpt.py
View File

@@ -81,7 +81,7 @@ def pre_process_datasets(encoded_datasets, input_len, cap_length, start_token, d
n_batch = len(dataset)
input_ids = np.zeros((n_batch, 2, input_len), dtype=np.int64)
mc_token_ids = np.zeros((n_batch, 2), dtype=np.int64)
lm_labels = np.full((n_batch, 2, input_len), fill_value=-100, dtype=np.int64)
lm_labels = np.full((n_batch, 2, input_len), fill_value=-1, dtype=np.int64)
mc_labels = np.zeros((n_batch,), dtype=np.int64)
for i, (story, cont1, cont2, mc_label), in enumerate(dataset):
with_cont1 = [start_token] + story[:cap_length] + [delimiter_token] + cont1[:cap_length] + [clf_token]