utils.py

import logging


def set_logger(log_file):
    logging.basicConfig(
        format='%(asctime)s %(levelname)-8s %(message)s',
        level=logging.INFO,
        datefmt='%Y-%m-%d %H:%M:%S',
        filename=log_file,
        filemode='w'
    )
    console = logging.StreamHandler()
    console.setLevel(logging.INFO)
    formatter = logging.Formatter('%(asctime)s %(levelname)-8s %(message)s')
    console.setFormatter(formatter)
    logging.getLogger('').addHandler(console)


class ScheduledOptim():
    '''A simple wrapper class for learning rate scheduling'''
    def __init__(self, optimizer, lr_mul, d_model, n_warmup_steps):
        self._optimizer = optimizer
        self.lr_mul = lr_mul
        self.d_model = d_model
        self.n_warmup_steps = n_warmup_steps
        self.n_steps = 0

    def step(self):
        "Step with the inner optimizer"
        self._update_learning_rate()
        self._optimizer.step()


    def zero_grad(self):
        "Zero out the gradients with the inner optimizer"
        self._optimizer.zero_grad()


    def _get_lr_scale(self):
        d_model = self.d_model
        n_steps, n_warmup_steps = self.n_steps, self.n_warmup_steps
        return (d_model ** -0.5) * min(n_steps ** (-0.5), n_steps * n_warmup_steps ** (-1.5))


    def _update_learning_rate(self):
        ''' Learning rate scheduling per step '''
        self.n_steps += 1
        lr = self.lr_mul * self._get_lr_scale()

        for param_group in self._optimizer.param_groups:
            param_group['lr'] = lr