ABINet-OCR / configs /pretrain_language_model.yaml
tomofi's picture
Add application file
cb433d6
global:
name: pretrain-language-model
phase: train
stage: pretrain-language
workdir: workdir
seed: ~
dataset:
train: {
roots: ['data/WikiText-103.csv'],
batch_size: 4096
}
test: {
roots: ['data/WikiText-103_eval_d1.csv'],
batch_size: 4096
}
training:
epochs: 80
show_iters: 50
eval_iters: 6000
save_iters: 3000
optimizer:
type: Adam
true_wd: False
wd: 0.0
bn_wd: False
clip_grad: 20
lr: 0.0001
args: {
betas: !!python/tuple [0.9, 0.999], # for default Adam
}
scheduler: {
periods: [70, 10],
gamma: 0.1,
}
model:
name: 'modules.model_language.BCNLanguage'
language: {
num_layers: 4,
loss_weight: 1.,
use_self_attn: False
}