ALBERT vs BERT diff

LICENSE

@@ -186,7 +186,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright [yyyy] [name of copyright owner]
+   Copyright 2019 Tae Hwan Jung
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.
@@ -198,4 +198,4 @@
    distributed under the License is distributed on an "AS IS" BASIS,
    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    See the License for the specific language governing permissions and
-   limitations under the License.
+   limitations under the License.

classify.py

@@ -171,7 +171,7 @@ def forward(self, input_ids, segment_ids, input_mask):
 
 def main(task='mrpc',
          train_cfg='config/train_mrpc.json',
-         model_cfg='config/bert_base.json',
+         model_cfg='config/albert_base.json',
          data_file='../glue/MRPC/train.tsv',
          model_file=None,
          pretrain_file='../uncased_L-12_H-768_A-12/bert_model.ckpt',

config/albert_base.json

@@ -0,0 +1,13 @@
+{
+	"embedding" : 128,
+
+	"hidden": 768,
+	"hidden_ff": 3072,
+
+	"n_layers": 12,
+	"n_heads": 12,
+	"max_len": 512,
+	"n_segments": 2,
+	"vocab_size": 30522
+}
+

config/albert_unittest.json

@@ -0,0 +1,12 @@
+{
+	"embedding" : 24,
+
+	"hidden": 64,
+	"hidden_ff": 256,
+
+	"n_layers": 6,
+	"n_heads": 1,
+	"max_len": 512,
+	"n_segments": 2,
+	"vocab_size": 30522
+}

config/bert_base.json

@@ -9,4 +9,3 @@
 	"n_segments": 2,
 	"vocab_size": 30522
 }
-

config/pretrain.json

@@ -1,9 +1,9 @@
 {
     "seed": 3431,
-    "batch_size": 96,
+    "batch_size": 8,
     "lr": 1e-4,
     "n_epochs": 25,
     "warmup": 0.1,
     "save_steps": 10000,
     "total_steps": 1000000
-}
+}