readme
Browse files
README.md
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# DistilBERT with word2vec token embeddings
|
2 |
+
|
3 |
+
This model has a word2vec token embedding matrix with 256k entries. The word2vec was trained on 100GB data from C4, MSMARCO, News, Wikipedia, S2ORC, for 3 epochs.
|
4 |
+
|
5 |
+
Then the model was trained on this dataset with MLM for 250k steps (batch size 64). The token embeddings were NOT updated.
|