Run !python src/main.py --train data/02-21.10way.clean --dev data/22.auto.clean --vocab data/vocab.json --model data/my_model

[lanhtruonggiang-k63a5]

[dynet] random seed: 3637392249
[dynet] allocating memory: 2000MB
[dynet] memory allocation done.
L2 regularization: 0
Hidden units: 200, per-LSTM units: 200
Embeddings: word=(44392, 50) tag=(48, 20)
Dropout rate: 0.5
Parameters initialized in [-0.01, 0.01]
Random UNKing parameter z = 0.8375
Exploration: alpha=1.0 beta=0
Loaded 39832 training sentences (3984 batches of size 10)!
Loaded 1700 validation trees!
........... epoch 1 ...........
The dy.parameter(...) call is now DEPRECATED.
There is no longer need to explicitly add parameters to the computation graph.
Any used parameter will be added automatically.
Traceback (most recent call last):
File "src/main.py", line 206, in
beta=args.beta,
File "/content/span-parser/src/network.py", line 472, in train
) for example in batch
File "/content/span-parser/src/network.py", line 472, in
) for example in batch
File "/content/span-parser/src/parser.py", line 340, in exploration
action = fm.l_action(action_index)
File "/content/span-parser/src/features.py", line 185, in l_action
return 'label-' + self.list(ldict.keys()[index - 1])
AttributeError: 'FeatureMapper' object has no attribute 'list'