\- Minimum number of epochs to train
\- Maximum number of epochs to train
\- l2 regularization coefficient
\- Initial number of steps in decay strategy
\- If loss after a SGD epochs haven't improved (absolutely) more than lossEps, then training is stopped
\- Seed for random
\- Level of verbosity during training procedure
\- Initial number of steps in decay strategy
\- l2 regularization coefficient
\- If loss after a SGD epochs haven't improved (absolutely) more than lossEps, then training is stopped
\- Maximum number of epochs to train
\- Minimum number of epochs to train
\- Seed for random
\- Level of verbosity during training procedure
Hyper Parameters and Setting for LinearChainCrf training
\- Minimum number of epochs to train
\- Maximum number of epochs to train
\- l2 regularization coefficient
\- Initial number of steps in decay strategy
\- If loss after a SGD epochs haven't improved (absolutely) more than lossEps, then training is stopped
\- Seed for random
\- Level of verbosity during training procedure