parent
83fd9589a1
commit
402770f193
@ -0,0 +1,44 @@
|
||||
###########################################################
|
||||
# DATA SETTING #
|
||||
###########################################################
|
||||
dataset_type: Ernie
|
||||
train_path: data/iwslt2012_zh/train.txt
|
||||
dev_path: data/iwslt2012_zh/dev.txt
|
||||
test_path: data/iwslt2012_zh/test.txt
|
||||
batch_size: 64
|
||||
num_workers: 2
|
||||
data_params:
|
||||
pretrained_token: ernie-3.0-nano-zh
|
||||
punc_path: data/iwslt2012_zh/punc_vocab
|
||||
seq_len: 100
|
||||
|
||||
|
||||
###########################################################
|
||||
# MODEL SETTING #
|
||||
###########################################################
|
||||
model_type: ErnieLinear
|
||||
model:
|
||||
pretrained_token: ernie-3.0-nano-zh
|
||||
num_classes: 4
|
||||
|
||||
###########################################################
|
||||
# OPTIMIZER SETTING #
|
||||
###########################################################
|
||||
optimizer_params:
|
||||
weight_decay: 1.0e-6 # weight decay coefficient.
|
||||
|
||||
scheduler_params:
|
||||
learning_rate: 1.0e-5 # learning rate.
|
||||
gamma: 0.9999 # scheduler gamma must between(0.0, 1.0) and closer to 1.0 is better.
|
||||
|
||||
###########################################################
|
||||
# TRAINING SETTING #
|
||||
###########################################################
|
||||
max_epoch: 20
|
||||
num_snapshots: 5
|
||||
|
||||
###########################################################
|
||||
# OTHER SETTING #
|
||||
###########################################################
|
||||
num_snapshots: 10 # max number of snapshots to keep while training
|
||||
seed: 42 # random seed for paddle, random, and np.random
|
Loading…
Reference in new issue