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

[rabbitcj]

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,
}

[xyzhou-puck]

Hi, please modify "data_path": "./data/douban/data_small.pkl", to "./data/douban/data.pkl" and try it again.

Xiangyang

[rabbitcj]

After modifing "data_path", it works. Why?

[xyzhou-puck]

After modifing "data_path", it works. Why?

Because ``data_small.pkl" is for code-debug and it only has a few training instances.