The matching scores are all equal when training and the model can not converge.

I am trying to train the model on douban data named "data_small.pkl" .
**My question:** The matching scores are all equal when training and the model can not converge.

The data is downloaded from the link in “ReadMe.txt”.
- tersorflow 1.8
- python 3.5

**1. Here is the dir structrue.**

```
data/douban/
|-- data.pkl
|-- data_small.pkl
|-- dev.txt
|-- test.txt
|-- train.txt
|-- word2id
`-- word_embedding.pkl
```
**2. Here, here's the `main.py` for training.**

```
conf = {
"data_path": "./data/douban/data_small.pkl",
"save_path": "./output/douban/DAM/",
"word_emb_init": "./data/douban/word_embedding.pkl",
"init_model": None, #"./output/douban/DAM_cross/DAM.ckpt", #should be set for test

"rand_seed": None,

"drop_dense": None,
"drop_attention": None,

"is_mask": True,
"is_layer_norm": True,
"is_positional": False,

"stack_num": 5,
"attention_type": "dot",

"learning_rate": 1e-3,
"vocab_size": 172130, #434512
"emb_size": 200,
"batch_size": 256, #200 for test

"max_turn_num": 9,
"max_turn_len": 50,

"max_to_keep": 1,
"num_scan_data": 2,
"_EOS_": 1, #28270
"final_n_class": 1,
}
```

Start with the training configuration in main.py and reproduce the reported behavior using data/douban/data_small.pkl with the stated Python 3.5 and TensorFlow 1.8 setup. Inspect the referenced data files and README instructions, then determine why the matching scores remain equal and define completion as training that produces non-equal scores and converges.

Written by the indexing model from the issue text.